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 49152
    5. 8-RES_FS49152-JB
    6. 45922
    Prev
    Next
    INDEX
    Explanations

    references to specific types of personalities or social roles, particularly masculine traits

    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
    605
    +0.10
    0.5%
    288
    +0.10
    0.5%
    57
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.10
    0.01
    116
    +0.10
    0.01
    137
    +0.10
    0.01
    Negative Logits
    dfx
    -0.82
     Leone
    -0.82
     Antiqu
    -0.80
     Ley
    -0.79
     Rack
    -0.78
     Jagu
    -0.77
    Aid
    -0.76
     Wand
    -0.76
    stall
    -0.75
    osuke
    -0.74
    POSITIVE LOGITS
     fide
    0.87
     blocker
    0.84
     particle
    0.81
     discharge
    0.79
     delta
    0.79
     miner
    0.77
     decay
    0.77
     fractions
    0.75
     parity
    0.74
     concentration
    0.73
    Activations Density 0.007%

    No Known Activations