© 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. 1796
    Prev
    Next
    INDEX
    Explanations

    words related to threats, risks, and dangerous situations

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of danger

    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
    ergy
    -0.84
    orney
    -0.79
    owned
    -0.79
    olitan
    -0.75
    anmar
    -0.71
    issance
    -0.70
    urally
    -0.69
    guyen
    -0.67
    ulous
    -0.65
    eenth
    -0.64
    POSITIVE LOGITS
    ously
    0.93
     lurking
    0.93
     lur
    0.89
     posed
    0.83
     Danger
    0.83
     endanger
    0.81
    lessly
    0.80
    mong
    0.79
    crow
    0.77
    danger
    0.74
    Activations Density 0.027%

    No Known Activations