© 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
    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. 11261
    Prev
    Next
    INDEX
    Explanations

    phrases related to details or specifics, especially in a professional or formal context

    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
    214
    +0.02
    0.5%
    137
    +0.02
    0.4%
    414
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.02
    0.04
    636
    +0.02
    0.02
    406
    +0.02
    0.02
    Negative Logits
    venant
    -0.14
    ftime
    -0.13
    cliffe
    -0.13
    ometer
    -0.12
     Maiden
    -0.12
    Äĩ
    -0.12
    former
    -0.12
    avior
    -0.12
    ibling
    -0.11
    continental
    -0.11
    POSITIVE LOGITS
     surpr
    0.15
     incent
    0.14
     discretion
    0.13
     Thumbnails
    0.13
     arrang
    0.13
     nep
    0.13
    PK
    0.13
     horm
    0.13
    PLA
    0.13
     dilig
    0.12
    Activations Density 0.188%

    No Known Activations