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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 1731
    Prev
    Next
    INDEX
    Explanations

    words related to compliance or agreement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    151
    +0.14
    0.6%
    8
    +0.12
    0.5%
    572
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.14
    0.03
    8
    +0.12
    0.02
    761
    +0.09
    0.02
    Negative Logits
    ns
    -0.79
    gart
    -0.77
    ilies
    -0.73
    ij士
    -0.71
    onso
    -0.69
    adem
    -0.69
    acco
    -0.68
    inction
    -0.68
    pert
    -0.67
    ricanes
    -0.67
    POSITIVE LOGITS
    side
    0.78
     stairs
    0.75
    wagon
    0.73
    ments
    0.72
    ities
    0.68
     nicely
    0.65
     prec
    0.65
     side
    0.64
    iously
    0.64
    leys
    0.63
    Activations Density 0.037%

    No Known Activations