© 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. 14100
    Prev
    Next
    INDEX
    Explanations

    functions or operations within code snippets

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to programming concepts and definitions

    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
     Ãĸ
    -0.71
     Reich
    -0.71
     OPS
    -0.69
     Sharif
    -0.68
     Trou
    -0.67
     FY
    -0.66
     Punjab
    -0.66
     UNESCO
    -0.65
     Zika
    -0.64
     Koz
    -0.64
    POSITIVE LOGITS
    DeliveryDate
    1.20
    Null
    1.12
    User
    1.10
    Own
    1.09
    Integer
    1.06
    Edge
    1.05
    Entity
    1.04
    Function
    1.04
    Array
    1.04
    Button
    1.03
    Activations Density 0.102%

    No Known Activations