© 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. 21087
    Prev
    Next
    INDEX
    Explanations

    words related to missiles and nuclear weapons

    oai_token-act-pair · gpt-3.5-turbo

    terms related to missile and nuclear threats

    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
    gres
    -1.01
    ĸļ
    -0.95
    mbuds
    -0.75
     coli
    -0.73
    ween
    -0.73
    greSQL
    -0.70
    orses
    -0.70
    xy
    -0.69
     Crim
    -0.68
    ime
    -0.67
    POSITIVE LOGITS
     launcher
    1.32
     launchers
    1.27
     warheads
    1.25
     missile
    1.20
     missiles
    1.18
     Launcher
    1.07
     batteries
    1.07
     submarines
    1.07
     destroyer
    1.07
     submarine
    1.04
    Activations Density 0.062%

    No Known Activations