© 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. 12421
    Prev
    Next
    INDEX
    Explanations

    concepts related to warning or potential negative outcomes

    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
    393
    +0.21
    1.0%
    362
    +0.15
    0.7%
    124
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.21
    0.08
    393
    +0.15
    0.06
    608
    +0.11
    0.06
    Negative Logits
     whenever
    -0.85
     instead
    -0.75
     periodically
    -0.72
     accordingly
    -0.72
     Leilan
    -0.69
     followed
    -0.68
    Rex
    -0.66
     shortly
    -0.66
     irrespective
    -0.66
     namely
    -0.65
    POSITIVE LOGITS
     slightest
    1.74
     same
    1.09
     usual
    1.06
     requisite
    1.04
     entirety
    0.99
     totality
    0.92
     faint
    0.85
     complexities
    0.84
     nor
    0.83
     sophistication
    0.82
    Activations Density 0.256%

    No Known Activations