© 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. 10211
    Prev
    Next
    INDEX
    Explanations

    numbers and special characters

    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
    377
    +0.13
    0.6%
    675
    +0.10
    0.4%
    118
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    524
    +0.13
    0.02
    284
    +0.10
    0.02
    232
    +0.09
    0.02
    Negative Logits
    oids
    -0.96
    oidal
    -0.85
    oid
    -0.79
    apsed
    -0.68
    dfx
    -0.68
    ographically
    -0.67
    ppelin
    -0.66
     brakes
    -0.64
    enegger
    -0.64
    oted
    -0.64
    POSITIVE LOGITS
    âĤ¬
    1.24
    ¯¯
    1.04
    ¯
    0.99
    ¸
    0.98
    ´
    0.97
    ¢
    0.94
    ÙĦ
    0.93
    tre
    0.93
    ¬
    0.93
    ¯¯¯¯
    0.93
    Activations Density 0.042%

    No Known Activations