© 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. 7-RES-JB
    11. 13420
    Prev
    Next
    INDEX
    Explanations

    references to illicit activities and markets on the dark web

    oai_token-act-pair · gpt-3.5-turbo

    references to the dark web and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.73
    veyard
    -0.68
    qualified
    -0.66
    verified
    -0.66
    idav
    -0.64
    ãĥīãĥ©
    -0.63
    upper
    -0.61
    terms
    -0.60
    STAR
    -0.59
    SEA
    -0.59
    POSITIVE LOGITS
     ®
    0.85
    eers
    0.73
    ographers
    0.69
    âĦ¢
    0.66
     Reloaded
    0.65
    eering
    0.63
    edly
    0.62
     affair
    0.62
    ®
    0.60
    sed
    0.60
    Activations Density 0.311%

    No Known Activations