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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 4413
    Prev
    Next
    INDEX
    Explanations

    words related to sexual content

    oai_token-act-pair · gpt-3.5-turbo

    explicit and sexual themes in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.85
    ETF
    -0.80
     condem
    -0.80
     Kessler
    -0.75
    KEN
    -0.75
    é¾
    -0.73
     helicop
    -0.72
    Weather
    -0.69
     Components
    -0.69
     FEMA
    -0.69
    POSITIVE LOGITS
     slut
    1.20
     erotic
    1.19
     sexy
    1.09
     sex
    1.08
     nude
    1.06
     pussy
    1.06
     kissing
    1.04
     porn
    1.04
    Sexual
    1.03
     horny
    1.03
    Activations Density 0.577%

    No Known Activations