© 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. 6151
    Prev
    Next
    INDEX
    Explanations

    time-related expressions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant events or experiences for the first time

    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
    CHAT
    -0.65
    ancies
    -0.60
    ancel
    -0.59
    haar
    -0.57
     Journals
    -0.57
    avorite
    -0.57
     tomat
    -0.56
    leted
    -0.55
     livelihood
    -0.52
    armor
    -0.52
    POSITIVE LOGITS
     ever
    1.37
     EVER
    1.30
    ever
    1.22
     since
    1.13
     imaginable
    0.95
    nas
    0.76
     lately
    0.72
     Ever
    0.71
    Ever
    0.71
     consecut
    0.69
    Activations Density 0.046%

    No Known Activations