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

    Neuronpedia

    APICircuit 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. 1-RES-JB
    6. 18396
    Prev
    Next
    INDEX
    Explanations

    phrases with an emphasis on a certain part of the human body

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "ass."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kubrick
    -0.75
    MSN
    -0.73
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
    ttes
    -0.64
    ONT
    -0.63
    EH
    -0.63
    âĢ¢âĢ¢
    -0.62
     Kramer
    -0.62
     Parkinson
    -0.61
     Kore
    -0.58
    POSITIVE LOGITS
    imilation
    1.51
    sembly
    1.10
     ass
    1.07
    ortment
    1.04
    ass
    1.03
    itude
    1.00
    assin
    0.99
    itance
    0.98
    umption
    0.96
    asin
    0.94
    Activations Density 0.006%

    No Known Activations