© 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. 20904
    Prev
    Next
    INDEX
    Explanations

    action verbs related to physical activity or bodily functions

    oai_token-act-pair · gpt-3.5-turbo

    key actions and characteristics related to various groups and societal issues

    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
     thereof
    -0.59
    clone
    -0.59
     Reboot
    -0.58
    apple
    -0.56
    nesday
    -0.56
     Panzer
    -0.55
    ople
    -0.55
     Ange
    -0.55
    Cub
    -0.54
     Gators
    -0.54
    POSITIVE LOGITS
     tremendous
    1.14
     disproportionately
    1.13
     enormous
    1.09
     vastly
    1.06
     billions
    1.03
     immense
    1.02
     disproportionate
    1.02
     trillions
    1.00
     vast
    0.98
     considerable
    0.98
    Activations Density 0.524%

    No Known Activations