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

    Neuronpedia

    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. 8792
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions, specifically related to narcotic reversal and its effects

    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
    203
    +0.10
    0.5%
    263
    +0.09
    0.4%
    317
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.10
    0.03
    403
    +0.09
    0.03
    335
    +0.09
    0.03
    Negative Logits
    ById
    -0.84
    soDeliveryDate
    -0.81
    shit
    -0.73
     Armageddon
    -0.73
     creeps
    -0.71
     messing
    -0.70
    atron
    -0.68
     $_
    -0.68
     piss
    -0.68
     Unicorn
    -0.67
    POSITIVE LOGITS
     hypothesized
    1.14
     analyses
    1.07
     hypotheses
    1.05
     hypothesis
    1.04
    ivariate
    1.01
    Discussion
    0.99
    Study
    0.98
     hypothes
    0.98
     study
    0.97
     findings
    0.95
    Activations Density 0.197%

    No Known Activations