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

    Neuronpedia

    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. 1344
    Prev
    Next
    INDEX
    Explanations

    mentions of militant groups and conflicts

    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
    314
    +0.12
    0.6%
    208
    +0.12
    0.5%
    556
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    664
    +0.12
    0.04
    556
    +0.12
    0.04
    193
    +0.09
    0.04
    Negative Logits
     consolid
    -0.61
    Compare
    -0.59
     geo
    -0.58
     shifts
    -0.54
    yz
    -0.52
     mileage
    -0.52
    quickShipAvailable
    -0.52
    GMT
    -0.52
     resulting
    -0.51
     satellite
    -0.51
    POSITIVE LOGITS
    ayers
    1.02
    aurus
    0.99
    leeve
    0.96
    avior
    0.93
    wered
    0.91
    atisf
    0.90
    olution
    0.85
    ourced
    0.85
    aying
    0.84
    omew
    0.84
    Activations Density 0.137%

    No Known Activations