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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 768
    9. 8-RES_FS768-JB
    11. 706
    Prev
    Next
    INDEX
    Explanations

    information related to scientific studies and medical conditions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    365
    +0.10
    0.4%
    760
    +0.09
    0.4%
    472
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    252
    +0.10
    0.11
    118
    +0.09
    0.08
    365
    +0.09
    0.03
    Negative Logits
    soDeliveryDate
    -1.19
     Franch
    -0.89
    books
    -0.88
    DragonMagazine
    -0.84
    selage
    -0.84
    Company
    -0.84
    yright
    -0.78
    Tokens
    -0.74
     rooft
    -0.73
    htaking
    -0.73
    POSITIVE LOGITS
     inflammation
    1.48
     neurological
    1.47
     metabolic
    1.43
     susceptibility
    1.41
     disease
    1.41
     cardiovascular
    1.40
     lesions
    1.39
     physiological
    1.39
     symptoms
    1.38
     biomark
    1.38
    Activations Density 5.535%

    No Known Activations