© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 2974
    Prev
    Next
    INDEX
    Explanations

    words related to sports scores and outcomes

    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
    496
    +0.12
    0.6%
    373
    +0.11
    0.5%
    599
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    631
    +0.12
    0.02
    599
    +0.11
    0.02
    696
    +0.10
    0.02
    Negative Logits
     realism
    -0.71
     misinformation
    -0.67
     shorth
    -0.64
     treating
    -0.64
     Anxiety
    -0.63
     owl
    -0.62
    lessly
    -0.60
     Equity
    -0.60
     Ashton
    -0.58
     diagn
    -0.58
    POSITIVE LOGITS
    gments
    1.37
    venth
    1.34
    eker
    1.26
    ems
    1.19
    vered
    1.16
    gment
    1.14
    eming
    1.10
    ldom
    1.08
    vere
    1.08
    mination
    1.07
    Activations Density 0.015%

    No Known Activations