© 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. 3067
    Prev
    Next
    INDEX
    Explanations

    personal pronouns such as "me" and "myself" when described alongside an action or attribute

    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
    314
    +0.12
    0.5%
    481
    +0.12
    0.5%
    225
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.12
    0.02
    39
    +0.12
    0.02
    225
    +0.11
    0.02
    Negative Logits
    luster
    -0.64
     Heist
    -0.63
    ordinate
    -0.59
    eatures
    -0.59
    ensibly
    -0.59
     Billboard
    -0.57
     Armageddon
    -0.57
     Anthem
    -0.57
     Beir
    -0.57
     Charleston
    -0.57
    POSITIVE LOGITS
     who
    0.78
    tics
    0.74
    thritis
    0.72
    zech
    0.69
    çĶ
    0.67
     inclined
    0.66
     ourselves
    0.66
     whom
    0.65
    å¸
    0.65
    agi
    0.65
    Activations Density 0.054%

    No Known Activations