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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9144
    Prev
    Next
    INDEX
    Explanations

    names of people involved in a physical altercation

    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
    +0.13
    0.6%
    430
    +0.12
    0.6%
    420
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.13
    0.07
    224
    +0.12
    0.06
    401
    +0.11
    0.06
    Negative Logits
    soDeliveryDate
    -0.71
    category
    -0.70
     endorsements
    -0.66
     Pione
    -0.65
    interstitial
    -0.64
     Recent
    -0.64
    isSpecialOrderable
    -0.62
    bitious
    -0.62
     Albania
    -0.62
    actionDate
    -0.61
    POSITIVE LOGITS
     panicked
    1.18
     proceeded
    1.17
     hesitated
    1.15
     intervened
    1.12
     retali
    1.11
     responded
    1.11
     grabbed
    1.10
     remembers
    1.09
     replied
    1.07
     promptly
    1.07
    Activations Density 0.313%

    No Known Activations