© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 11283
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of sweating

    oai_token-act-pair · gpt-3.5-turbo

    references to physical sensations and clothing, especially sweaters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pax
    -0.84
     Drone
    -0.70
    olars
    -0.69
     FX
    -0.69
     Peak
    -0.68
    etus
    -0.66
    amus
    -0.65
     Orbital
    -0.65
     Padres
    -0.64
    anyon
    -0.63
    POSITIVE LOGITS
     swe
    3.93
     sweater
    1.33
     tal
    1.26
    hatt
    0.98
     batt
    0.97
    swe
    0.95
     Nigel
    0.93
     floral
    0.92
     ra
    0.92
     fing
    0.89
    Activations Density 0.037%

    No Known Activations