© 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 49152
    9. 8-RES_FS49152-JB
    11. 25944
    Prev
    Next
    INDEX
    Explanations

    references to wind and atmospheric conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    27
    +0.12
    0.5%
    375
    +0.09
    0.4%
    718
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.12
    0.02
    326
    +0.09
    0.01
    538
    +0.09
    0.01
    Negative Logits
    xus
    -0.77
    Ô
    -0.71
    endants
    -0.67
     Identity
    -0.67
     Flavoring
    -0.66
     Lives
    -0.65
    ity
    -0.64
    utical
    -0.64
    esson
    -0.64
     Bour
    -0.64
    POSITIVE LOGITS
     gust
    1.16
     blowing
    1.06
     currents
    1.01
     winds
    0.99
     blew
    0.93
     turbines
    0.93
    storms
    0.91
    burst
    0.88
     turbine
    0.86
     turbulence
    0.84
    Activations Density 0.013%

    No Known Activations