Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 41418
    Prev
    Next
    INDEX
    Explanations

    references to societal groups and their characteristics

    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
    216
    +0.13
    0.6%
    679
    +0.12
    0.5%
    756
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    216
    +0.13
    0.02
    679
    +0.12
    0.02
    577
    +0.11
    0.02
    Negative Logits
    Delivery
    -0.87
    SIGN
    -0.68
    shire
    -0.68
     Maker
    -0.66
    inventoryQuantity
    -0.65
    DAY
    -0.64
    god
    -0.64
     Keeper
    -0.63
    rence
    -0.62
    mosp
    -0.62
    POSITIVE LOGITS
    naires
    0.92
    ifier
    0.90
    think
    0.87
    ifiers
    0.86
    ifications
    0.86
     affili
    0.85
    roups
    0.84
    folk
    0.83
    ification
    0.82
    achu
    0.81
    Activations Density 0.028%

    No Known Activations