© 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. 21215
    Prev
    Next
    INDEX
    Explanations

    references to problems, issues, or bugs in a software context

    oai_token-act-pair · gpt-3.5-turbo

    suggestions and possibilities for actions or methods to be taken

    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
     Mour
    -0.74
     gloom
    -0.68
    isconsin
    -0.68
    cknow
    -0.66
     endorsing
    -0.64
     hypoc
    -0.63
    dor
    -0.63
     Wend
    -0.63
    raising
    -0.63
    aukee
    -0.63
    POSITIVE LOGITS
     bugs
    1.09
     happ
    1.06
     usability
    1.00
     interoper
    1.00
     annoy
    0.99
     overwrite
    0.98
     automate
    0.98
     buggy
    0.97
     happen
    0.97
     occur
    0.96
    Activations Density 0.252%

    No Known Activations