© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6333
    Prev
    Next
    INDEX
    Explanations

    codes for programming functions and methods

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    440
    +0.17
    0.6%
    447
    +0.13
    0.5%
    739
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.17
    0.03
    739
    +0.13
    0.02
    440
    +0.12
    0.02
    Negative Logits
    ylum
    -1.16
     laun
    -1.14
    avorite
    -1.08
     Canaver
    -1.05
    xual
    -1.00
    halla
    -0.97
    vez
    -0.95
    umenthal
    -0.94
     neighb
    -0.94
    eatures
    -0.93
    POSITIVE LOGITS
    ----------------------------------------------------------------
    1.29
    ////////////////////////////////
    1.26
    ################
    1.22
     ----------------------------------------------------------------
    1.19
    ////////////////
    1.16
    include
    1.14
    ================================================================
    1.14
    ERROR
    1.10
    ################################
    1.09
    define
    1.08
    Activations Density 0.114%

    No Known Activations