© 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. 1899
    Prev
    Next
    INDEX
    Explanations

    words related to threats, harm, or endangerment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to threats to public health and safety

    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
    lich
    -0.74
    DragonMagazine
    -0.72
    hari
    -0.67
    zeb
    -0.67
     differs
    -0.66
    zag
    -0.66
    otom
    -0.66
     Edited
    -0.65
    lists
    -0.65
     apiece
    -0.65
    POSITIVE LOGITS
     livelihood
    1.46
     integrity
    1.43
     wellbeing
    1.38
     viability
    1.35
     credibility
    1.28
     reputation
    1.22
     competitiveness
    1.15
     stability
    1.14
     fragile
    1.14
     psyche
    1.11
    Activations Density 0.257%

    No Known Activations