© 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 EvalsExportsinterp-engineNEWAPI 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. 13478
    Prev
    Next
    INDEX
    Explanations

    mentions of significant events or incidents reported by news outlets

    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
    373
    +0.20
    0.9%
    314
    +0.10
    0.5%
    313
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.20
    0.04
    634
    +0.10
    0.04
    508
    +0.10
    0.04
    Negative Logits
     screws
    -0.66
     pend
    -0.65
     barg
    -0.61
     Malfoy
    -0.60
     brill
    -0.59
     supposedly
    -0.59
     swast
    -0.58
     mascot
    -0.57
    comes
    -0.57
     sled
    -0.57
    POSITIVE LOGITS
    News
    0.89
     reporters
    0.82
     News
    0.80
     interviewer
    0.78
     reporter
    0.76
     Insight
    0.76
    aretz
    0.75
     correspondent
    0.74
     Observer
    0.73
    news
    0.73
    Activations Density 0.111%

    No Known Activations