© 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. 21096
    Prev
    Next
    INDEX
    Explanations

    structured programming code snippets containing opening and closing curly braces

    oai_token-act-pair · gpt-3.5-turbo

    technical elements or coding syntax associated with structured sets and data representations

    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
     Fruit
    -0.82
    Jenn
    -0.80
    OHN
    -0.78
     Adams
    -0.76
     Adrian
    -0.75
    ghost
    -0.75
     Pear
    -0.75
     surv
    -0.74
    Adams
    -0.74
    ournal
    -0.73
    POSITIVE LOGITS
    set
    1.89
     Set
    1.88
    Set
    1.88
     set
    1.82
     SET
    1.75
    sets
    1.74
     Sets
    1.73
     sets
    1.68
    SET
    1.60
    setting
    1.38
    Activations Density 0.131%

    No Known Activations