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. 2185
    Prev
    Next
    INDEX
    Explanations

    words related to legal and political issues

    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
    329
    +0.10
    0.4%
    336
    +0.09
    0.4%
    553
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.07
    654
    +0.09
    0.05
    665
    +0.09
    0.07
    Negative Logits
    rill
    -0.69
    iller
    -0.68
    iris
    -0.66
    rians
    -0.66
    zon
    -0.63
    flush
    -0.63
    gin
    -0.62
    enaries
    -0.62
    ppa
    -0.61
     weep
    -0.61
    POSITIVE LOGITS
     laws
    1.10
     regulations
    1.08
     norms
    1.06
     Laws
    1.04
     strict
    0.98
     statutes
    0.96
     obligations
    0.95
     guidelines
    0.95
     directives
    0.94
     Rule
    0.94
    Activations Density 1.278%

    No Known Activations