Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18798
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the act of spitting

    oai_token-act-pair · gpt-3.5-turbo

    actions related to spitting and similar expressions of forceful exhalation

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

    No Comments

    Negative Logits
    algia
    -0.67
    alty
    -0.65
    Reviewer
    -0.63
    annis
    -0.63
    âĹ¼
    -0.63
     Passage
    -0.62
    ITNESS
    -0.61
    ifestyle
    -0.60
     facult
    -0.60
    Focus
    -0.60
    POSITIVE LOGITS
     spit
    0.94
    fires
    0.89
    ting
    0.84
    ters
    0.84
     spat
    0.83
    balls
    0.81
    ball
    0.80
    hell
    0.79
    fire
    0.75
    bowl
    0.74
    Activations Density 0.013%

    No Known Activations