© 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 EvalsExportsAPI 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. 14934
    Prev
    Next
    INDEX
    Explanations

    items listed in a structured format, typically including various categories or topics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "listed."

    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
    ework
    -0.69
    icz
    -0.64
    Sense
    -0.61
     Curve
    -0.58
    NEY
    -0.57
    ICH
    -0.56
     Sco
    -0.56
    Pac
    -0.55
    scape
    -0.55
    qua
    -0.54
    POSITIVE LOGITS
     alphabet
    1.20
     below
    1.01
     geographically
    0.99
     therein
    0.96
     prominently
    0.95
     tradem
    0.92
     separately
    0.91
     underneath
    0.87
     herein
    0.87
     beside
    0.86
    Activations Density 0.109%

    No Known Activations