© 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. 12797
    Prev
    Next
    INDEX
    Explanations

    mentions of people in political positions or political events

    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
    224
    +0.11
    0.5%
    314
    +0.10
    0.5%
    146
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.11
    0.02
    371
    +0.10
    0.02
    224
    +0.09
    0.02
    Negative Logits
    acters
    -0.79
    Sea
    -0.78
    pots
    -0.71
    VALUE
    -0.70
    Prev
    -0.68
    hered
    -0.67
    riks
    -0.67
    ãĥ¼ãĤ¯
    -0.66
    boxes
    -0.66
    ters
    -0.66
    POSITIVE LOGITS
     Eric
    0.77
     Pam
    0.76
     Accountability
    0.76
     nominee
    0.76
     Sessions
    0.75
    istration
    0.74
     Assembly
    0.73
     prosecutor
    0.73
     Prosecutor
    0.71
     Janet
    0.70
    Activations Density 0.020%

    No Known Activations