© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10198
    Prev
    Next
    INDEX
    Explanations

    terms related to animals and physical characteristics

    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
    727
    +0.11
    0.5%
    211
    +0.10
    0.5%
    603
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.05
    326
    +0.10
    0.04
    48
    +0.09
    0.03
    Negative Logits
     Seym
    -0.86
     guiActiveUnfocused
    -0.79
     Settlement
    -0.77
    raint
    -0.76
     Fabric
    -0.68
     Sett
    -0.66
     mine
    -0.64
    english
    -0.63
     Leilan
    -0.63
    ographically
    -0.61
    POSITIVE LOGITS
    ggle
    1.17
    «
    1.13
    keye
    1.06
    gencies
    1.04
    kered
    0.99
    ª
    0.97
    gars
    0.92
    keley
    0.92
    pled
    0.92
    ched
    0.91
    Activations Density 0.157%

    No Known Activations