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 24576
    5. 8-RES_FS24576-JB
    6. 1413
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental positions, administrative bodies, and political issues

    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
    480
    +0.29
    1.4%
    447
    +0.20
    1.0%
    420
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.29
    0.04
    105
    +0.20
    0.04
    647
    +0.12
    0.04
    Negative Logits
    inventoryQuantity
    -0.85
    dad
    -0.65
    )}
    -0.65
    ĪĴ
    -0.65
    this
    -0.64
    Guard
    -0.64
     anymore
    -0.63
    laughs
    -0.63
     regrets
    -0.62
    else
    -0.62
    POSITIVE LOGITS
     varied
    0.70
     eclectic
    0.70
     diverse
    0.63
     sleek
    0.62
     distinctive
    0.59
    krit
    0.59
     consist
    0.59
     meticulously
    0.59
    undown
    0.58
     orally
    0.58
    Activations Density 0.820%

    No Known Activations