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. 22307
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to nudity

    oai_token-act-pair · gpt-3.5-turbo

    references to nudity or being naked

    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
    ENCY
    -0.76
    ãĥ£
    -0.73
    enges
    -0.73
    MER
    -0.70
    EFF
    -0.69
    abul
    -0.69
    ENTS
    -0.69
    vernment
    -0.68
    dule
    -0.68
    riers
    -0.68
    POSITIVE LOGITS
     mole
    1.07
    ity
    0.86
    ness
    0.86
     naked
    0.81
    legged
    0.78
     nude
    0.76
     selfies
    0.75
     selfie
    0.74
     breasts
    0.74
     silhou
    0.74
    Activations Density 0.036%

    No Known Activations