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. 11538
    Prev
    Next
    INDEX
    Explanations

    phrases related to military service and government controversies

    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
    314
    +0.15
    0.7%
    73
    +0.10
    0.5%
    363
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    363
    +0.15
    0.04
    639
    +0.10
    0.03
    463
    +0.09
    0.03
    Negative Logits
    threat
    -0.73
    fulness
    -0.68
    lihood
    -0.67
    00007
    -0.67
    livious
    -0.65
    RP
    -0.64
    URR
    -0.63
    ebin
    -0.61
     999
    -0.61
    Requ
    -0.60
    POSITIVE LOGITS
     woman
    0.95
     women
    0.94
     Woman
    0.85
    Woman
    0.80
     female
    0.80
     WOM
    0.77
     boys
    0.75
     girls
    0.74
     girl
    0.72
     females
    0.70
    Activations Density 0.131%

    No Known Activations