© 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 49152
    9. 8-RES_FS49152-JB
    11. 25722
    Prev
    Next
    INDEX
    Explanations

    words that appear to be variations or forms of the root "gen" or its related derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    373
    +0.13
    0.6%
    109
    +0.11
    0.5%
    164
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.05
    232
    +0.11
    0.04
    373
    +0.10
    -0.01
    Negative Logits
    actionDate
    -0.78
     Protocol
    -0.70
    uyomi
    -0.69
    externalActionCode
    -0.68
    dayName
    -0.66
     horizon
    -0.63
    ailable
    -0.62
    Demand
    -0.61
    ailability
    -0.60
    ĸļ
    -0.60
    POSITIVE LOGITS
    reau
    0.86
    wine
    0.82
    anamo
    0.79
    gio
    0.76
     Sisters
    0.75
    stan
    0.75
    wald
    0.74
    iola
    0.73
    agall
    0.73
    elson
    0.70
    Activations Density 0.122%

    No Known Activations