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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 12282
    Prev
    Next
    INDEX
    Explanations

    terms related to the buttocks

    oai_token-act-pair · gpt-3.5-turbo

    references to buttocks or bottoms, often in humorous or derogatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MSN
    -0.84
    é¾įå
    -0.72
    BuyableInstoreAndOnline
    -0.72
     effic
    -0.65
     Flavoring
    -0.63
     Catalonia
    -0.62
     Mub
    -0.62
    GROUP
    -0.61
     Nare
    -0.61
     predec
    -0.60
    POSITIVE LOGITS
    holes
    1.63
    imilation
    1.44
     cheeks
    1.24
    hole
    1.15
    asin
    1.01
    hol
    0.94
     cheek
    0.90
    itance
    0.89
    heads
    0.88
    plug
    0.86
    Activations Density 0.031%

    No Known Activations