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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19123
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative, political, and legal contexts

    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
    36
    +0.17
    0.8%
    362
    +0.13
    0.6%
    736
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.17
    0.07
    362
    +0.13
    0.05
    250
    +0.13
    0.04
    Negative Logits
    enance
    -0.79
    coins
    -0.75
     reacts
    -0.74
    facts
    -0.72
     idols
    -0.71
    agents
    -0.71
     gays
    -0.70
     seats
    -0.69
     shares
    -0.69
     prefers
    -0.69
    POSITIVE LOGITS
     broader
    1.13
     larger
    1.10
     wider
    1.04
     constellation
    1.02
     continuum
    0.98
     series
    0.97
     concerted
    0.97
     trilogy
    0.92
     growing
    0.91
     longstanding
    0.89
    Activations Density 0.158%

    No Known Activations