© 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. 10122
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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
    566
    +0.13
    0.6%
    385
    +0.12
    0.5%
    538
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.02
    288
    +0.12
    0.02
    128
    +0.11
    0.02
    Negative Logits
     awa
    -0.68
    ĪĴ
    -0.65
     Airways
    -0.64
     bankruptcy
    -0.59
     faults
    -0.58
    foundland
    -0.58
     Levant
    -0.57
     Turks
    -0.56
    ãĥ£
    -0.56
    terday
    -0.55
    POSITIVE LOGITS
    heast
    1.37
    heastern
    1.32
    gage
    1.13
    iculture
    1.08
    oise
    1.04
    icultural
    0.99
    nikov
    0.95
    oad
    0.90
    ality
    0.90
    imer
    0.89
    Activations Density 0.111%

    No Known Activations