© 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. 14911
    Prev
    Next
    INDEX
    Explanations

    sentences mentioning the word "face"

    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
    260
    +0.13
    0.6%
    195
    +0.11
    0.5%
    512
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.13
    0.03
    435
    +0.11
    0.02
    549
    +0.10
    0.02
    Negative Logits
    iculture
    -0.76
    selves
    -0.75
    æ©Ł
    -0.74
    icult
    -0.72
    akings
    -0.68
    self
    -0.67
    icultural
    -0.65
    ancies
    -0.65
    hester
    -0.64
    RY
    -0.64
    POSITIVE LOGITS
    plate
    1.03
    plant
    1.00
    BOOK
    0.92
    offs
    0.89
     veil
    0.85
    beard
    0.83
    plates
    0.82
    breakers
    0.79
     mask
    0.77
     masks
    0.76
    Activations Density 0.041%

    No Known Activations