© 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. 15364
    Prev
    Next
    INDEX
    Explanations

    names of political figures

    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
    447
    +0.30
    1.6%
    481
    +0.23
    1.2%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.30
    0.07
    481
    +0.23
    0.06
    346
    +0.10
    0.05
    Negative Logits
    âĹ¼
    -0.78
    é¾įå
    -0.77
    Els
    -0.69
    }.
    -0.68
    âĶĢâĶĢâĶĢâĶĢ
    -0.66
    _.
    -0.66
     Azerb
    -0.66
    Ô
    -0.65
    åĮ
    -0.61
    omever
    -0.60
    POSITIVE LOGITS
     celebrates
    0.78
     awoke
    0.78
     unveiled
    0.78
     prepares
    0.76
     announced
    0.76
     announces
    0.76
     enters
    0.75
     has
    0.73
     reacts
    0.73
     apologised
    0.73
    Activations Density 0.401%

    No Known Activations