© 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. 9639
    Prev
    Next
    INDEX
    Explanations

    information related to government actions, policies, and reports

    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
    480
    +0.43
    2.2%
    447
    +0.13
    0.6%
    266
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.43
    0.11
    480
    +0.13
    0.01
    266
    +0.10
    0.10
    Negative Logits
     compat
    -0.73
     die
    -0.65
     teammate
    -0.63
     teammates
    -0.63
    die
    -0.62
     brun
    -0.59
    owan
    -0.59
     companions
    -0.58
    tein
    -0.58
     classmates
    -0.58
    POSITIVE LOGITS
     antitrust
    0.82
     prosecuting
    0.79
     appoint
    0.79
     investigating
    0.79
     subsid
    0.78
     oversight
    0.78
     intervene
    0.78
     jurisdiction
    0.78
     sanction
    0.76
     regulating
    0.76
    Activations Density 1.430%

    No Known Activations