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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 11734
    Prev
    Next
    INDEX
    Explanations

    sexual and erotic terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual activities and explicit content

    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
    é¾
    -0.79
    APD
    -0.75
     FEMA
    -0.74
    é¾įå¥ij士
    -0.72
    REE
    -0.72
     Canaver
    -0.72
    £ı
    -0.71
    ETF
    -0.70
     Brewery
    -0.69
     condem
    -0.68
    POSITIVE LOGITS
     erotic
    1.22
     sex
    1.11
     nude
    1.10
     slut
    1.10
     virginity
    1.08
     kissing
    1.07
     pussy
    1.06
     sexy
    1.06
     nipples
    1.05
     boobs
    1.05
    Activations Density 0.349%

    No Known Activations