© 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. 21097
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals in military uniforms

    oai_token-act-pair · gpt-3.5-turbo

    instances of "in a" followed by descriptions involving uniforms or clothing

    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
    ESA
    -0.69
    ebin
    -0.67
    once
    -0.67
    onics
    -0.65
    ICO
    -0.65
     Creatures
    -0.64
    onto
    -0.62
     Pwr
    -0.62
    RAM
    -0.62
    MAP
    -0.62
    POSITIVE LOGITS
     jeans
    1.35
     camouflage
    1.30
     robes
    1.29
     sunglasses
    1.29
     fatig
    1.29
     uniform
    1.24
     disguise
    1.21
     trousers
    1.17
     suits
    1.12
     shorts
    1.10
    Activations Density 0.098%

    No Known Activations