© 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. 15468
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues, such as class divisions and legislative processes

    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
    481
    +0.15
    0.7%
    447
    +0.11
    0.5%
    67
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.07
    67
    +0.11
    0.06
    152
    +0.10
    0.06
    Negative Logits
    ĸļ
    -1.02
    omial
    -0.75
    esthetic
    -0.72
    obyl
    -0.72
    wcsstore
    -0.70
    arium
    -0.70
     tremend
    -0.70
    igation
    -0.69
    iggurat
    -0.69
    utra
    -0.68
    POSITIVE LOGITS
     individuals
    1.39
     youths
    1.37
     travelers
    1.34
     citizens
    1.33
     residents
    1.27
     travellers
    1.26
     professionals
    1.25
     youngsters
    1.23
     communities
    1.22
     immigrants
    1.22
    Activations Density 0.312%

    No Known Activations