© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 8377
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific individuals or events

    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
    373
    +0.18
    0.6%
    289
    +0.14
    0.5%
    239
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.05
    659
    +0.14
    0.04
    767
    +0.14
    0.04
    Negative Logits
    iquid
    -1.08
    istrate
    -0.92
    è¦ļéĨĴ
    -0.90
    paces
    -0.87
    owler
    -0.87
    spring
    -0.86
     Qiao
    -0.86
    DERR
    -0.85
    worn
    -0.84
     hawk
    -0.84
    POSITIVE LOGITS
    eker
    1.26
    llers
    1.19
    venth
    1.16
    xy
    1.16
    ller
    1.14
    rette
    1.12
    ption
    1.11
    gger
    1.11
    ptic
    1.09
    lled
    1.09
    Activations Density 0.670%

    No Known Activations