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 49152
    5. 8-RES_FS49152-JB
    6. 37064
    Prev
    Next
    INDEX
    Explanations

    terms related to medical research and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    232
    +0.13
    0.6%
    373
    +0.12
    0.6%
    756
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.03
    326
    +0.12
    0.03
    145
    +0.12
    0.02
    Negative Logits
     diligence
    -0.75
     aggro
    -0.71
     ess
    -0.70
     behavi
    -0.66
     karma
    -0.63
     goodwill
    -0.63
     manslaughter
    -0.62
     anonymity
    -0.61
     tyr
    -0.61
     weaker
    -0.61
    POSITIVE LOGITS
     Problems
    1.10
     Replacement
    1.07
     Lessons
    1.05
     Functions
    1.05
     Favorite
    1.03
     Uses
    1.03
     Issues
    1.00
     Challenges
    0.98
     Patterns
    0.97
     Structure
    0.97
    Activations Density 0.136%

    No Known Activations