© 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. 11716
    Prev
    Next
    INDEX
    Explanations

    statements concerning conflicts, battles, political positions, or controversial societal topics

    oai_token-act-pair · gpt-3.5-turbo

    themes related to conflict and struggle

    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
     Kissinger
    -0.60
     Hutchinson
    -0.60
     Canaver
    -0.58
     epigen
    -0.57
     Howell
    -0.56
     Keynes
    -0.55
     Gaddafi
    -0.55
     Hubbard
    -0.55
     Morris
    -0.54
     Chomsky
    -0.53
    POSITIVE LOGITS
    âĢ
    1.59
     âĢ
    1.17
    âĹ
    1.13
    âľ
    1.07
    ãĢ
    1.03
    âĢł
    1.00
    à
    1.00
    âĸł
    0.97
    ï¸ı
    0.96
    âĸ
    0.95
    Activations Density 1.314%

    No Known Activations