© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11445
    Prev
    Next
    INDEX
    Explanations

    statements related to actions taken by individuals or entities, especially regarding self-defense, bad faith, malice, and authorization

    oai_token-act-pair · gpt-3.5-turbo

    references to self-defense in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĵĺ
    -0.83
    etheless
    -0.78
     âĵĺ
    -0.73
    achev
    -0.73
    »Ĵ
    -0.72
    pora
    -0.70
     Dates
    -0.69
    Versions
    -0.66
     Stories
    -0.66
    azines
    -0.61
    POSITIVE LOGITS
     malice
    1.03
     impulse
    0.95
    intention
    0.95
     reckless
    0.92
    authorized
    0.91
     haste
    0.89
     reck
    0.89
     negligence
    0.87
     negligent
    0.86
     behest
    0.85
    Activations Density 0.270%

    No Known Activations