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. 7-RES-JB
    6. 5679
    Prev
    Next
    INDEX
    Explanations

    references to body parts, especially the buttocks

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "butt" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.69
     horm
    -0.67
    ktop
    -0.66
    chid
    -0.64
    vernment
    -0.64
    agents
    -0.63
     Journals
    -0.63
    restricted
    -0.61
    ership
    -0.61
    vous
    -0.61
    POSITIVE LOGITS
     cheeks
    1.09
    plug
    1.01
    butt
    0.99
    ocks
    0.93
     cheek
    0.88
     butt
    0.87
    orted
    0.85
    iary
    0.84
    ock
    0.84
    minster
    0.79
    Activations Density 0.029%

    No Known Activations