© 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. 15516
    Prev
    Next
    INDEX
    Explanations

    the word "alone" used to emphasize a point or situation

    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
    99
    +0.10
    0.5%
    726
    +0.10
    0.4%
    651
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.10
    0.02
    39
    +0.10
    0.01
    656
    +0.10
    0.01
    Negative Logits
     horm
    -0.66
     Briggs
    -0.65
     lockout
    -0.64
     Boyle
    -0.63
    anty
    -0.62
    uay
    -0.61
     Antar
    -0.61
     symmetry
    -0.61
    itely
    -0.58
    EMP
    -0.57
    POSITIVE LOGITS
     exceeds
    0.78
    ieth
    0.76
     suffice
    0.76
     constitutes
    0.73
    åŃIJ
    0.69
     proves
    0.69
     amounted
    0.69
     accounted
    0.68
    SPONSORED
    0.68
     exceeded
    0.67
    Activations Density 0.025%

    No Known Activations