© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 11741
    Prev
    Next
    INDEX
    Explanations

    commands or directives in structured text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of phrases related to inappropriate behavior or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mathemat
    -0.90
     vulner
    -0.84
     challeng
    -0.79
     unnecess
    -0.76
    enegger
    -0.76
     accomp
    -0.73
     disadvant
    -0.73
     elig
    -0.72
     suspic
    -0.72
     occas
    -0.72
    POSITIVE LOGITS
    ution
    0.85
    ï¸ı
    0.79
    hare
    0.77
    ence
    0.77
    undo
    0.75
    eous
    0.73
    tale
    0.72
    urry
    0.72
    uilding
    0.72
    ĸļ
    0.72
    Activations Density 0.078%

    No Known Activations