© 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. 21020
    Prev
    Next
    INDEX
    Explanations

    names of people related to expert opinions

    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
    +0.29
    1.3%
    430
    +0.11
    0.5%
    241
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.29
    0.08
    368
    +0.11
    0.07
    302
    +0.09
    0.07
    Negative Logits
     disappearing
    -0.64
    Quantity
    -0.62
    clusive
    -0.60
    GET
    -0.60
    TOR
    -0.58
    ãĥĸ
    -0.58
     eternity
    -0.58
    Tokens
    -0.56
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.56
    animate
    -0.56
    POSITIVE LOGITS
     meanwhile
    1.14
     gave
    1.05
     echoed
    1.04
     intervened
    1.01
     took
    1.00
     reacted
    1.00
     commented
    1.00
     agrees
    0.97
     wrote
    0.97
     disagrees
    0.96
    Activations Density 0.587%

    No Known Activations