© 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. 7563
    Prev
    Next
    INDEX
    Explanations

    instances of the word "spit" at varying strengths

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spit" and related terms

    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
    ipolar
    -0.78
    stract
    -0.78
     Puzzles
    -0.75
     robotics
    -0.72
     gener
    -0.72
    boxing
    -0.70
    kus
    -0.70
     Hemp
    -0.68
    opoly
    -0.68
    merce
    -0.68
    POSITIVE LOGITS
     spit
    1.94
     parish
    1.73
     frontline
    1.63
     spitting
    1.59
     Parish
    1.39
     Tyr
    1.09
     Spit
    1.04
     dashboard
    1.04
     Flan
    1.04
     saliva
    1.01
    Activations Density 0.067%

    No Known Activations