© 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. 12-RES-JB
    11. 2978
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a strategy related to a specific activity or game

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    strategic game terminology and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Tolkien
    -0.75
    blance
    -0.75
     Huffington
    -0.72
    Wisconsin
    -0.71
     Caption
    -0.70
     Clifford
    -0.70
    ãĤ±
    -0.70
     Rowling
    -0.70
     Albuquerque
    -0.69
     Literature
    -0.69
    POSITIVE LOGITS
     turrets
    1.12
     siege
    1.10
     harass
    1.09
     barracks
    1.07
     creep
    1.07
     minerals
    1.04
     marines
    1.04
     nexus
    1.03
     mineral
    1.03
     mines
    1.03
    Activations Density 0.088%

    No Known Activations