© 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. 2811
    Prev
    Next
    INDEX
    Explanations

    references to the action of taking something and using it in a specific way

    oai_token-act-pair · gpt-3.5-turbo

    repeated conjunctions that connect phrases or ideas

    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
    meet
    -0.68
    onica
    -0.65
    ADVERTISEMENT
    -0.64
    ooter
    -0.64
    çķ
    -0.64
     Lack
    -0.62
     Citizen
    -0.61
    unci
    -0.61
    ractor
    -0.60
    Ag
    -0.60
    POSITIVE LOGITS
     paste
    0.96
     shove
    0.95
     THEN
    0.92
     toss
    0.91
     put
    0.90
     rese
    0.87
     then
    0.86
     send
    0.86
     upload
    0.86
     shipped
    0.85
    Activations Density 0.242%

    No Known Activations