© 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 12288
    9. 8-RES_FS12288-JB
    11. 9461
    Prev
    Next
    INDEX
    Explanations

    political and governmental references, particularly related to investigations, policy, and officials

    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
    350
    +0.14
    0.6%
    481
    +0.12
    0.5%
    430
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.14
    0.05
    645
    +0.12
    0.05
    748
    +0.12
    0.04
    Negative Logits
    POST
    -0.80
    aves
    -0.74
    ets
    -0.73
    GET
    -0.71
    fuck
    -0.70
    urgy
    -0.69
    ucks
    -0.68
    BIP
    -0.68
    SPA
    -0.68
    blocks
    -0.67
    POSITIVE LOGITS
     deputy
    1.03
     former
    1.02
     Deputy
    0.99
     representatives
    0.98
     colleagues
    0.97
     others
    0.92
     Chief
    0.92
     Vice
    0.91
     businessman
    0.89
     drummer
    0.89
    Activations Density 0.379%

    No Known Activations