© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 3489
    Prev
    Next
    INDEX
    Explanations

    phrases related to drawbacks, issues, problems, and concerns

    oai_token-act-pair · gpt-3.5-turbo

    terms related to flaws or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olon
    -0.82
    ongyang
    -0.78
    ewitness
    -0.70
    velt
    -0.66
    uilding
    -0.65
    ucha
    -0.63
    riel
    -0.63
    ership
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.61
    baugh
    -0.60
    POSITIVE LOGITS
     inherent
    1.00
     drawback
    0.97
     encountered
    0.89
     drawbacks
    0.85
     caveats
    0.83
     pitfalls
    0.83
     complicate
    0.82
     posed
    0.81
     caveat
    0.79
     pesky
    0.78
    Activations Density 0.243%

    No Known Activations