© 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. 4-RES-JB
    11. 7255
    Prev
    Next
    INDEX
    Explanations

    words related to potential dangers or risks

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of hazards

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

    No Comments

    Negative Logits
    gdala
    -1.03
    ebus
    -0.99
    artney
    -0.87
    olitan
    -0.83
    ergy
    -0.82
    ainers
    -0.82
    itton
    -0.79
    zos
    -0.79
    este
    -0.77
    atters
    -0.76
    POSITIVE LOGITS
     hazards
    1.13
    ously
    1.04
     hazard
    1.04
     mitigation
    0.86
     endanger
    0.86
     deterrent
    0.77
     lurking
    0.77
     lur
    0.73
     danger
    0.71
     peril
    0.71
    Activations Density 0.017%

    No Known Activations