© 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. 20918
    Prev
    Next
    INDEX
    Explanations

    acronyms and organizational titles

    oai_token-act-pair · gpt-3.5-turbo

    references to universities and educational institutions

    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
    •Starts with {letter} features
    S

    No Comments

    Negative Logits
     Dion
    -0.83
     Boll
    -0.82
    ģ«
    -0.79
     Bengals
    -0.79
     marqu
    -0.78
     Marqu
    -0.77
     Ambro
    -0.74
     Cornel
    -0.73
     Haram
    -0.72
     prol
    -0.70
    POSITIVE LOGITS
    SS
    1.48
    SA
    1.31
    S
    1.29
    sg
    1.23
    SR
    1.20
    SG
    1.20
    SE
    1.19
    SI
    1.19
    SD
    1.18
    ss
    1.18
    Activations Density 1.013%

    No Known Activations