© 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. 11-RES-JB
    11. 23953
    Prev
    Next
    INDEX
    Explanations

    references to nakedness and nudity

    oai_token-act-pair · gpt-3.5-turbo

    references to nudity and sexual themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.91
    soType
    -0.72
     Blizz
    -0.69
     Flavoring
    -0.68
     issuer
    -0.64
    kson
    -0.64
    IELD
    -0.64
    ICA
    -0.63
     Burnett
    -0.63
    REE
    -0.62
    POSITIVE LOGITS
     masturb
    1.02
     ejac
    0.99
     fetish
    0.94
     orgasm
    0.92
     sex
    0.91
     pics
    0.90
     genitals
    0.86
    Sexual
    0.86
     slut
    0.86
     masturbation
    0.85
    Activations Density 0.177%

    No Known Activations