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. 931
    Prev
    Next
    INDEX
    Explanations

    mentions related to legislation and policy changes

    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
    481
    +0.31
    1.5%
    680
    +0.14
    0.6%
    159
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.31
    0.05
    159
    +0.14
    0.06
    362
    +0.10
    0.07
    Negative Logits
    outube
    -0.67
     Photographer
    -0.67
    Posts
    -0.66
    eye
    -0.66
    VIDIA
    -0.63
     fishes
    -0.63
     bask
    -0.63
    ontent
    -0.63
    Ub
    -0.62
     Passion
    -0.62
    POSITIVE LOGITS
     legislation
    1.47
     proposed
    1.26
     proposal
    1.25
     amendment
    1.21
     legisl
    1.20
     amendments
    1.18
     regulations
    1.18
     proposals
    1.16
     draconian
    1.16
     repeal
    1.14
    Activations Density 0.638%

    No Known Activations