© 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. 0-RES-JB
    11. 12527
    Prev
    Next
    INDEX
    Explanations

    words related to nuclear weapons development

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to stealth or stealth abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Argon
    -0.75
    iped
    -0.69
     Libre
    -0.64
    ecided
    -0.64
     Manufacturer
    -0.62
     CoC
    -0.62
     Colour
    -0.61
     coloured
    -0.60
     electroly
    -0.60
     vacc
    -0.60
    POSITIVE LOGITS
    ascript
    0.79
    Beck
    0.74
    vich
    0.72
    restling
    0.71
     Kaufman
    0.69
    hn
    0.69
    sha
    0.67
    itz
    0.66
     fool
    0.65
    %]
    0.65
    Activations Density 0.000%

    No Known Activations