© 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 24576
    9. 8-RES_FS24576-JB
    11. 8583
    Prev
    Next
    INDEX
    Explanations

    social media and website names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    +0.12
    0.6%
    731
    +0.11
    0.5%
    205
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.12
    0.03
    373
    +0.11
    -0.02
    482
    +0.10
    0.02
    Negative Logits
    paces
    -0.74
    ¶
    -0.67
     Incarn
    -0.62
    clus
    -0.60
    cephal
    -0.60
    gat
    -0.58
    gage
    -0.57
    gom
    -0.57
    bang
    -0.57
    gew
    -0.57
    POSITIVE LOGITS
    azo
    0.74
    TextColor
    0.71
     Cancel
    0.69
    duction
    0.68
     Email
    0.65
    Reason
    0.62
     });
    0.61
    ornia
    0.59
    actory
    0.58
    uterte
    0.58
    Activations Density 0.137%

    No Known Activations