© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17382
    Prev
    Next
    INDEX
    Explanations

    text related to intelligence, legislation, and critical commentary

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    87
    +0.28
    1.4%
    447
    +0.15
    0.8%
    481
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.28
    0.07
    146
    +0.15
    0.06
    224
    +0.09
    0.06
    Negative Logits
    pired
    -0.57
     sexes
    -0.54
    ))))
    -0.53
    ").
    -0.53
     span
    -0.52
     mattered
    -0.52
    pires
    -0.52
    ¯¯¯¯
    -0.51
     hull
    -0.51
     });
    -0.51
    POSITIVE LOGITS
     Productions
    0.61
     Magazine
    0.60
     Ventures
    0.59
     whereby
    0.58
     Analytics
    0.57
     Labs
    0.56
    !,
    0.55
     Gloss
    0.53
    's
    0.53
     (@
    0.53
    Activations Density 0.676%

    No Known Activations