© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18953
    Prev
    Next
    INDEX
    Explanations

    industrial terms, specifically related to technology and business

    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
    481
    +0.17
    0.8%
    447
    +0.12
    0.6%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.05
    423
    +0.12
    0.04
    724
    +0.12
    0.05
    Negative Logits
    tein
    -0.85
    reditary
    -0.78
    irin
    -0.74
    anamo
    -0.64
    Ô
    -0.62
     exerc
    -0.62
    empty
    -0.60
    ufficient
    -0.60
    hiro
    -0.59
    etime
    -0.57
    POSITIVE LOGITS
    atics
    0.97
     worldwide
    0.81
    wcs
    0.80
     today
    0.74
     itself
    0.73
    places
    0.73
    ifice
    0.71
    osphere
    0.70
     globally
    0.69
    eers
    0.69
    Activations Density 0.163%

    No Known Activations