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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 15422
    Prev
    Next
    INDEX
    Explanations

    mentions of tattoos

    oai_token-act-pair · gpt-3.5-turbo

    references to tattoos and body art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scill
    -0.72
    audi
    -0.69
    é¾
    -0.68
    EH
    -0.68
     Camb
    -0.68
    士
    -0.67
    AUD
    -0.67
    PF
    -0.65
    UTION
    -0.65
     AUD
    -0.64
    POSITIVE LOGITS
     tattoos
    1.06
     tattoo
    1.06
     pigment
    0.87
     Tatt
    0.78
     tatt
    0.77
     sleeve
    0.77
    rette
    0.77
     ink
    0.75
     painter
    0.74
     scars
    0.73
    Activations Density 0.015%

    No Known Activations