© 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. 1037
    Prev
    Next
    INDEX
    Explanations

    references to database and data management-related terms or concepts

    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
    288
    +0.22
    0.7%
    167
    +0.22
    0.7%
    216
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.22
    0.06
    653
    +0.22
    0.05
    289
    +0.14
    0.03
    Negative Logits
    ModLoader
    -1.25
    lain
    -1.15
    folios
    -1.06
     tremend
    -1.01
    awar
    -0.94
     notor
    -0.94
     Palestin
    -0.93
    ovie
    -0.90
     vow
    -0.90
    ength
    -0.88
    POSITIVE LOGITS
     analytics
    1.23
    flow
    1.20
    iologist
    1.17
     recorder
    1.09
    ãĤº
    1.06
     collection
    1.05
     collectors
    1.03
     collected
    1.01
    ãĥ©
    1.00
    Frames
    1.00
    Activations Density 0.777%

    No Known Activations