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

    Neuronpedia

    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. 2-RES-JB
    11. 17336
    Prev
    Next
    INDEX
    Explanations

    words related to adult content, specifically the word "porn"

    oai_token-act-pair · gpt-3.5-turbo

    references to pornography and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IELD
    -0.85
    WAYS
    -0.83
    âĸ¬
    -0.82
    姫
    -0.76
     Quin
    -0.71
    IFE
    -0.70
     Brewer
    -0.69
     COUR
    -0.66
    externalActionCode
    -0.65
    âĸ¬âĸ¬
    -0.65
    POSITIVE LOGITS
    ographers
    1.03
    ographer
    0.95
    hub
    0.92
     pornography
    0.90
    ographically
    0.89
     porn
    0.85
    stars
    0.84
    asus
    0.83
    ographic
    0.80
    ography
    0.78
    Activations Density 0.012%

    No Known Activations