© 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. 6-RES-JB
    11. 9725
    Prev
    Next
    INDEX
    Explanations

    numerical sequences

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly percentages or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     psychiat
    -0.70
     outl
    -0.66
    Medic
    -0.65
     consecut
    -0.63
    minist
    -0.60
    manship
    -0.60
     misunder
    -0.59
    hetti
    -0.58
    neys
    -0.58
     foreseeable
    -0.58
    POSITIVE LOGITS
     Inquisitor
    0.70
    tro
    0.67
     Hel
    0.65
     largeDownload
    0.65
    ©¶æ¥µ
    0.65
     ILCS
    0.64
    ///
    0.63
     Conclusion
    0.61
    ================================================================
    0.61
    imov
    0.60
    Activations Density 0.072%

    No Known Activations