© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9678
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns mentioned in news articles

    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
    728
    +0.10
    0.5%
    654
    +0.10
    0.5%
    72
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.06
    284
    +0.10
    0.05
    373
    +0.09
    -0.02
    Negative Logits
    ËĪ
    -0.70
    kefeller
    -0.65
    quit
    -0.62
    xual
    -0.62
    Filename
    -0.61
    finder
    -0.60
     Velvet
    -0.57
    laws
    -0.56
    \/\/
    -0.56
    minecraft
    -0.56
    POSITIVE LOGITS
    icio
    0.85
    ãĤ¶
    0.80
    steen
    0.70
    cially
    0.69
    ador
    0.69
    iflower
    0.68
    ë
    0.67
    owship
    0.67
    reau
    0.67
    asar
    0.66
    Activations Density 0.321%

    No Known Activations