© 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
    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. 6095
    Prev
    Next
    INDEX
    Explanations

    people or things that have gone or left

    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
    153
    +0.04
    0.4%
    615
    +0.04
    0.4%
    300
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.04
    0.03
    287
    +0.04
    0.02
    94
    +0.04
    0.02
    Negative Logits
    netflix
    -0.33
    argon
    -0.31
    uyomi
    -0.30
    200000
    -0.29
    REP
    -0.29
     Liqu
    -0.29
    ulence
    -0.29
    atile
    -0.28
    ursed
    -0.28
    048
    -0.27
    POSITIVE LOGITS
     Yards
    0.34
     Nost
    0.30
    agles
    0.29
     Trend
    0.29
     Tomorrow
    0.29
     Orig
    0.28
    lihood
    0.28
    bats
    0.28
     Grove
    0.28
    conom
    0.27
    Activations Density 0.169%

    No Known Activations