© 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. 25980
    Prev
    Next
    INDEX
    Explanations

    negatives or criticisms related to political figures or events

    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
    314
    +0.22
    1.0%
    493
    +0.10
    0.5%
    143
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.22
    0.01
    152
    +0.10
    0.03
    115
    +0.10
    0.03
    Negative Logits
     exceptions
    -0.70
     execut
    -0.67
     footnote
    -0.67
     exponent
    -0.66
     bree
    -0.66
     (>
    -0.66
     overd
    -0.64
     braces
    -0.64
     (<
    -0.64
     relapse
    -0.63
    POSITIVE LOGITS
    friendly
    1.19
    themed
    1.15
    branded
    1.09
    owned
    1.07
    controlled
    1.07
    centric
    1.06
    related
    1.02
    aligned
    1.02
    induced
    1.01
    centered
    1.01
    Activations Density 0.026%

    No Known Activations