© 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. 14959
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and organizations in sports contexts

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    123
    +0.14
    0.7%
    314
    +0.14
    0.7%
    300
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.14
    0.09
    22
    +0.14
    0.08
    469
    +0.12
    0.06
    Negative Logits
    atel
    -0.68
    tar
    -0.65
    tre
    -0.64
    wine
    -0.63
    tein
    -0.62
    raid
    -0.61
    ersen
    -0.59
     captcha
    -0.59
    pard
    -0.57
    Null
    -0.57
    POSITIVE LOGITS
     regards
    1.10
    effic
    1.05
     terms
    1.04
    efficiency
    1.03
     spite
    0.97
    clusions
    0.94
     nutshell
    0.93
     lieu
    0.91
     accordance
    0.91
    clus
    0.88
    Activations Density 0.363%

    No Known Activations