© 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. 5850
    Prev
    Next
    INDEX
    Explanations

    conditional statements with a specific structure

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to legal or ethical violations

    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
    ardy
    -0.54
    ophon
    -0.52
     Cosponsors
    -0.51
    é¾įå
    -0.50
    anga
    -0.49
    ãĥĹ
    -0.48
    acio
    -0.47
    chieve
    -0.46
    aspberry
    -0.46
     nomine
    -0.45
    POSITIVE LOGITS
     then
    1.86
    then
    1.83
     THEN
    1.56
     Then
    1.32
    Then
    1.27
     please
    0.95
     PLEASE
    0.87
     it
    0.85
    thening
    0.83
    thens
    0.82
    Activations Density 0.717%

    No Known Activations