© 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. 13881
    Prev
    Next
    INDEX
    Explanations

    references to events or actions happening at a specific time or in a specific order

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the release of media or products in specific locations and times

    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
    accompan
    -0.66
    ¥
    -0.54
    aptic
    -0.53
    oplan
    -0.52
    igh
    -0.52
    MODE
    -0.50
     awaits
    -0.50
     inverse
    -0.49
     intangible
    -0.49
    "},"
    -0.48
    POSITIVE LOGITS
     nor
    1.89
    nor
    1.60
     anymore
    1.47
     until
    1.38
    until
    1.26
     till
    1.20
     either
    1.17
     whatsoever
    1.11
    yet
    1.09
    Nor
    0.99
    Activations Density 0.670%

    No Known Activations