© 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. 5430
    Prev
    Next
    INDEX
    Explanations

    specific programming statements or code-related keywords

    oai_token-act-pair · gpt-3.5-turbo

    operations related to database management or user data handling in programming contexts

    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
    /)
    -0.71
    /
    -0.70
    /,
    -0.65
    ãĢı
    -0.65
    âĢ¦)
    -0.65
     inducing
    -0.63
    ?),
    -0.61
     acron
    -0.61
     AMA
    -0.61
     birthplace
    -0.60
    POSITIVE LOGITS
     +=
    1.82
     -=
    1.52
     =
    1.50
    ++;
    1.41
     :=
    1.35
    +=
    1.05
    =(
    1.03
    ();
    1.03
    =$
    1.03
    Print
    0.99
    Activations Density 0.049%

    No Known Activations