© 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 EvalsExportsinterp-engineNEWAPI 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. 4833
    Prev
    Next
    INDEX
    Explanations

    specific terms related to academic institutions and events

    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
    447
    +0.38
    2.2%
    481
    +0.28
    1.6%
    87
    +0.19
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.38
    0.13
    481
    +0.28
    0.10
    67
    +0.19
    0.08
    Negative Logits
    =/
    -0.47
     Hamas
    -0.46
    ulhu
    -0.46
    fetched
    -0.45
     Hiroshima
    -0.44
    anwhile
    -0.44
     MSI
    -0.44
    orsche
    -0.43
     Canaver
    -0.43
    oldemort
    -0.43
    POSITIVE LOGITS
    Wiki
    0.66
    foundation
    0.52
     =================================================================
    0.51
    Pen
    0.48
    POST
    0.48
    MC
    0.47
     Era
    0.47
     Forums
    0.46
    Gear
    0.45
    $.
    0.45
    Activations Density 0.989%

    No Known Activations