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. 8363
    Prev
    Next
    INDEX
    Explanations

    phrases related to saving time, money, and effort

    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
    747
    +0.13
    0.6%
    223
    +0.12
    0.5%
    627
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    529
    +0.13
    0.02
    223
    +0.12
    0.02
    747
    +0.10
    0.02
    Negative Logits
    SPONSORED
    -1.04
    KER
    -0.72
    ç«
    -0.72
    女
    -0.71
    DEBUG
    -0.68
    cart
    -0.64
     solicitation
    -0.64
    bos
    -0.63
     encomp
    -0.63
    Constructed
    -0.63
    POSITIVE LOGITS
     bacon
    0.85
     penn
    0.83
     sanity
    0.79
     priceless
    0.78
     Lives
    0.76
    ockets
    0.75
    $$
    0.74
     valuable
    0.74
     precious
    0.74
     bucks
    0.73
    Activations Density 0.083%

    No Known Activations