© 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. 7-RES-JB
    11. 21101
    Prev
    Next
    INDEX
    Explanations

    explicit warnings or cautions in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize safety precautions and warnings

    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
    cart
    -0.69
     magically
    -0.67
     Founder
    -0.66
     descendants
    -0.63
     independents
    -0.62
    Spons
    -0.61
     creator
    -0.61
     Canad
    -0.60
    creator
    -0.60
    Joined
    -0.59
    POSITIVE LOGITS
     beware
    1.13
     precautions
    1.12
     caution
    1.11
     Avoid
    1.02
    Avoid
    0.99
    avoid
    0.98
     lest
    0.96
     carefully
    0.94
     heed
    0.94
     precaution
    0.92
    Activations Density 0.845%

    No Known Activations