© 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. 16365
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology products and specifications

    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%
    124
    +0.12
    0.6%
    678
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.17
    0.06
    652
    +0.12
    0.05
    289
    +0.09
    0.02
    Negative Logits
     Gw
    -0.73
     Fitz
    -0.71
     Suc
    -0.69
     Raw
    -0.69
     disbelief
    -0.68
     Wide
    -0.68
     Virgin
    -0.68
     Tend
    -0.67
    íķ
    -0.66
     Grav
    -0.66
    POSITIVE LOGITS
    aters
    1.08
    oops
    1.07
    atures
    1.06
    ules
    1.05
    iaries
    1.03
    eware
    1.03
    actions
    1.01
    lets
    1.00
    artments
    0.99
    let
    0.99
    Activations Density 0.240%

    No Known Activations