© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 13936
    Prev
    Next
    INDEX
    Explanations

    mentions of government and political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to high-ranking governmental and political officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wonderland
    -0.72
    ounded
    -0.70
    tiny
    -0.69
     LTD
    -0.67
    iverse
    -0.66
     Flores
    -0.64
    illions
    -0.64
     Roses
    -0.63
    Unique
    -0.61
    oute
    -0.60
    POSITIVE LOGITS
     negotiator
    1.24
     adviser
    1.02
     strategist
    1.01
     thinker
    0.95
     advisor
    0.93
     economist
    0.92
     officer
    0.92
     analyst
    0.90
     diplomat
    0.88
     proponent
    0.88
    Activations Density 0.195%

    No Known Activations