© 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. 10369
    Prev
    Next
    INDEX
    Explanations

    descriptions of medical conditions, treatments, and injuries

    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
    481
    +0.13
    0.6%
    121
    +0.10
    0.5%
    100
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.13
    0.08
    545
    +0.10
    0.04
    135
    +0.10
    0.04
    Negative Logits
     Faction
    -0.79
     Influence
    -0.78
     alliances
    -0.78
     Dominion
    -0.77
    advertising
    -0.77
    ahime
    -0.77
     Klux
    -0.75
     marketers
    -0.74
     BaseType
    -0.73
     fleets
    -0.73
    POSITIVE LOGITS
     hospitalized
    1.44
     healed
    1.39
     illness
    1.30
     symptoms
    1.30
     ailments
    1.29
     medically
    1.29
     surgery
    1.29
     hospital
    1.29
     coma
    1.26
     suffering
    1.24
    Activations Density 0.642%

    No Known Activations