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 3072
    5. 8-RES_FS3072-JB
    6. 2866
    Prev
    Next
    INDEX
    Explanations

    decisive actions or decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    70
    +0.11
    0.5%
    665
    +0.11
    0.5%
    7
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.11
    0.07
    665
    +0.11
    0.07
    750
    +0.10
    0.05
    Negative Logits
    anon
    -0.80
    eries
    -0.71
    attery
    -0.66
    awi
    -0.66
    amon
    -0.65
    abytes
    -0.65
    rongh
    -0.63
    agos
    -0.63
    acking
    -0.62
    resso
    -0.62
    POSITIVE LOGITS
     differently
    0.78
     unanimously
    0.77
     beforehand
    0.76
    ters
    0.73
     upon
    0.73
     unilaterally
    0.71
     randomly
    0.66
     Garc
    0.66
     calculus
    0.66
     anew
    0.66
    Activations Density 0.596%

    No Known Activations