© 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. 14931
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer security

    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
    87
    +0.38
    2.3%
    459
    +0.14
    0.9%
    516
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.38
    -0.03
    459
    +0.14
    0.11
    516
    +0.09
    0.05
    Negative Logits
     UNCLASSIFIED
    -0.75
     skelet
    -0.70
    etheless
    -0.59
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.59
     disadvant
    -0.58
    âĹ¼
    -0.56
    âķIJ
    -0.56
     exting
    -0.55
     Azerb
    -0.55
     pse
    -0.55
    POSITIVE LOGITS
     [âĢ¦]
    0.70
     âĢİ
    0.63
    âĢİ
    0.57
     âĢº
    0.56
     Donald
    0.53
    ↵Âł
    0.52
     ....
    0.52
     ...
    0.48
     Vinyl
    0.47
    ADVERTISEMENT
    0.47
    Activations Density 3.728%

    No Known Activations