© 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. 10106
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    519
    +0.10
    0.5%
    733
    +0.10
    0.4%
    101
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.10
    0.03
    238
    +0.10
    0.03
    576
    +0.10
    0.02
    Negative Logits
    HI
    -0.67
    rison
    -0.65
    aukee
    -0.61
    HAM
    -0.61
    hips
    -0.60
    rod
    -0.57
    én
    -0.57
     Gamble
    -0.57
    mma
    -0.56
    raq
    -0.56
    POSITIVE LOGITS
     the
    0.93
    the
    0.88
    rontal
    0.71
     Corpus
    0.68
     tha
    0.65
     The
    0.63
    Õ
    0.62
     THE
    0.62
    The
    0.60
     });
    0.59
    Activations Density 0.378%

    No Known Activations