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. 23308
    Prev
    Next
    INDEX
    Explanations

    information related to products, offers, and their descriptions

    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
    287
    +0.13
    0.6%
    397
    +0.11
    0.5%
    544
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    738
    +0.13
    0.03
    678
    +0.11
    0.03
    564
    +0.10
    0.03
    Negative Logits
    linux
    -0.93
    Northern
    -0.86
    TPPStreamerBot
    -0.85
    recent
    -0.83
    ussia
    -0.82
    DON
    -0.80
    Surv
    -0.80
    Southern
    -0.80
    surv
    -0.80
    affected
    -0.79
    POSITIVE LOGITS
     kit
    1.15
     sheet
    1.02
     box
    1.01
     plate
    1.01
     curtain
    0.97
     mask
    0.97
     sticker
    0.94
     bracelet
    0.94
     pack
    0.94
     button
    0.94
    Activations Density 0.192%

    No Known Activations