© 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. 9-RES-JB
    11. 15883
    Prev
    Next
    INDEX
    Explanations

    words related to danger and risk

    oai_token-act-pair · gpt-3.5-turbo

    references to danger or threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.71
    ulous
    -0.69
    eenth
    -0.66
    orney
    -0.66
    atters
    -0.65
    ergy
    -0.64
    GB
    -0.64
    pel
    -0.61
    guyen
    -0.60
    anmar
    -0.59
    POSITIVE LOGITS
    ously
    1.12
     lur
    1.01
     posed
    0.97
    ous
    0.94
     lurking
    0.88
     Danger
    0.84
     zone
    0.84
    OUS
    0.83
    saf
    0.83
     hazards
    0.81
    Activations Density 0.035%

    No Known Activations