© 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. 847
    Prev
    Next
    INDEX
    Explanations

    mentions of fundraising and charity activities

    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
    385
    +0.12
    0.6%
    608
    +0.11
    0.5%
    421
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.07
    385
    +0.11
    0.06
    13
    +0.11
    0.05
    Negative Logits
    ĸļ
    -0.87
    oplan
    -0.74
    iquette
    -0.72
    eme
    -0.70
    uli
    -0.69
    ept
    -0.69
    picture
    -0.68
    pring
    -0.68
    itude
    -0.68
    acting
    -0.67
    POSITIVE LOGITS
     charity
    1.14
     scholarships
    1.08
     fund
    1.06
     charities
    1.05
     upkeep
    1.02
     subsid
    1.00
     charitable
    0.99
     expenses
    0.96
     coffers
    0.92
     reimburse
    0.92
    Activations Density 0.383%

    No Known Activations