© 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. 10639
    Prev
    Next
    INDEX
    Explanations

    terms related to the adult entertainment industry

    oai_token-act-pair · gpt-3.5-turbo

    references to pornography and related topics

    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
     MacArthur
    -0.85
     Fei
    -0.67
    wcs
    -0.67
    ATHER
    -0.65
    abilities
    -0.65
     Rye
    -0.59
     Shake
    -0.59
     Boh
    -0.59
     Dew
    -0.59
    ees
    -0.58
    POSITIVE LOGITS
    ographers
    1.57
    ography
    1.39
    ographic
    1.34
    ographer
    1.33
    ographically
    1.21
    hub
    1.17
    ographies
    1.14
    OGR
    1.13
    ograp
    1.07
    stars
    1.06
    Activations Density 0.057%

    No Known Activations