© 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. 21151
    Prev
    Next
    INDEX
    Explanations

    elements related to programming code or syntax

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and structures related to data processing and programming

    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
    AMY
    -0.79
    BAT
    -0.75
    lishing
    -0.74
    Catal
    -0.74
    Chel
    -0.73
     Gutenberg
    -0.72
    agall
    -0.70
    BuyableInstoreAndOnline
    -0.69
    catentry
    -0.68
    Winged
    -0.66
    POSITIVE LOGITS
     ((
    1.08
     []
    1.07
     nil
    1.06
     ())
    1.04
     [(
    1.04
     ([
    0.95
     ()
    0.94
     expr
    0.94
     args
    0.93
     (_
    0.92
    Activations Density 0.053%

    No Known Activations