© 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 49152
    9. 8-RES_FS49152-JB
    11. 37511
    Prev
    Next
    INDEX
    Explanations

    medical terminology and conditions related to allergies and infections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    480
    +0.48
    2.5%
    266
    +0.10
    0.5%
    234
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.48
    0.01
    266
    +0.10
    0.07
    142
    +0.10
    0.03
    Negative Logits
    Untitled
    -0.82
     Franch
    -0.72
    Lenin
    -0.71
    Tokens
    -0.70
    Theme
    -0.68
    Marx
    -0.67
     horizont
    -0.67
    Flags
    -0.67
     Franchise
    -0.66
     scoreboard
    -0.66
    POSITIVE LOGITS
     Symptoms
    1.27
     patients
    1.26
     clinical
    1.24
     symptoms
    1.23
     clinically
    1.22
     dietary
    1.20
     nutritional
    1.20
     antibiotic
    1.19
     untreated
    1.18
     medications
    1.18
    Activations Density 0.676%

    No Known Activations