© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 Local
    9. 6-RES_SCL-AJT
    11. 33049
    Prev
    Next
    INDEX
    Explanations

    information related to step-by-step processes or instructions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.31
    1.4%
    481
    +0.19
    0.9%
    674
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    674
    +0.31
    0.12
    346
    +0.19
    0.12
    167
    +0.10
    -0.12
    Negative Logits
    .#
    -0.66
    âĢİ
    -0.64
    ...)
    -0.62
     âĢİ
    -0.60
     :-)
    -0.59
    Rh
    -0.59
    Nev
    -0.58
     yours
    -0.57
    ...
    -0.56
     (),
    -0.55
    POSITIVE LOGITS
    rontal
    0.81
    gradation
    0.76
    igrate
    0.64
    cised
    0.63
    poons
    0.63
    reditary
    0.62
     REPORT
    0.61
     guiName
    0.61
    ciating
    0.59
    iots
    0.58
    Activations Density 29.770%

    No Known Activations