© 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. 1155
    Prev
    Next
    INDEX
    Explanations

    the word "only" appearing before a numerical value

    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
    +0.17
    0.5%
    616
    +0.16
    0.5%
    737
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.17
    0.06
    616
    +0.16
    0.05
    219
    +0.16
    0.05
    Negative Logits
    aptic
    -1.03
    nation
    -1.00
    lat
    -0.97
    consumer
    -0.97
    velt
    -0.97
    insula
    -0.95
    del
    -0.95
    nat
    -0.95
    des
    -0.94
    staking
    -0.94
    POSITIVE LOGITS
     thing
    1.39
     reason
    1.34
     drawback
    1.32
     exception
    1.31
     remaining
    1.31
     conceivable
    1.25
     downside
    1.23
     surviving
    1.20
     clue
    1.14
     superpower
    1.13
    Activations Density 0.913%

    No Known Activations