Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8388
    Prev
    Next
    INDEX
    Explanations

    keywords related to hierarchy or ranking

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    679
    +0.15
    0.7%
    756
    +0.10
    0.5%
    276
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.15
    0.02
    679
    +0.10
    0.02
    198
    +0.10
    0.01
    Negative Logits
    \/\/
    -0.76
    argo
    -0.74
    reens
    -0.70
    ãĥĨãĤ£
    -0.70
    orescence
    -0.69
     Ezek
    -0.68
    issance
    -0.67
    pmwiki
    -0.67
     Pwr
    -0.65
    credit
    -0.65
    POSITIVE LOGITS
     insign
    1.05
    nance
    0.83
    enance
    0.81
    loader
    0.80
    ings
    0.79
     quo
    0.78
     outsider
    0.77
    ific
    0.73
    liness
    0.72
    irection
    0.72
    Activations Density 0.028%

    No Known Activations