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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22572
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions or bodily functions, particularly spitting and vomiting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spitting and vomiting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annis
    -0.73
    âĹ¼
    -0.67
    CONCLUS
    -0.65
    alty
    -0.64
    fman
    -0.64
    herty
    -0.63
     lawy
    -0.63
    isman
    -0.62
     Defenders
    -0.61
    onential
    -0.61
    POSITIVE LOGITS
     spit
    1.11
     spitting
    0.88
    fires
    0.84
    ball
    0.79
    oute
    0.77
    balls
    0.77
    ipes
    0.76
     spew
    0.75
    bowl
    0.74
    fire
    0.72
    Activations Density 0.007%

    No Known Activations