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

    Neuronpedia

    Jacobian LensNEW
    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. 10526
    Prev
    Next
    INDEX
    Explanations

    mentions of significant events, including crimes, conflicts, and political situations

    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
    159
    +0.15
    0.7%
    195
    +0.11
    0.5%
    709
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.15
    0.04
    402
    +0.11
    0.04
    621
    +0.10
    0.03
    Negative Logits
    ouls
    -0.91
    hips
    -0.85
    bows
    -0.79
    onies
    -0.77
    olas
    -0.72
    ships
    -0.69
    riages
    -0.68
    icides
    -0.68
    alties
    -0.67
    ivas
    -0.66
    POSITIVE LOGITS
     unnamed
    0.98
    worldly
    0.93
     aspect
    0.91
     notable
    0.90
     pecul
    0.89
     complication
    0.89
     possibility
    0.88
     drawback
    0.88
     unidentified
    0.87
     option
    0.87
    Activations Density 0.066%

    No Known Activations