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 768
    5. 8-RES_FS768-JB
    6. 68
    Prev
    Next
    INDEX
    Explanations

    statements expressing a strong belief and demand for recognition

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    762
    +0.11
    0.5%
    125
    +0.11
    0.5%
    246
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.11
    0.22
    567
    +0.11
    0.10
    756
    +0.11
    -0.10
    Negative Logits
     Reported
    -0.83
    arthed
    -0.79
    mentioned
    -0.79
    HB
    -0.79
     Reports
    -0.78
    Rail
    -0.78
    Update
    -0.78
    recent
    -0.77
    USS
    -0.76
    Sample
    -0.76
    POSITIVE LOGITS
     ideals
    1.34
     righteousness
    1.30
     dignity
    1.28
     individuality
    1.19
     humanity
    1.14
     nurture
    1.14
     spirituality
    1.13
     destiny
    1.13
     morality
    1.13
     truths
    1.09
    Activations Density 10.388%

    No Known Activations