© 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. 9-RES-JB
    11. 15840
    Prev
    Next
    INDEX
    Explanations

    words related to titles, such as "ace of spades" or "guardian angel."

    oai_token-act-pair · gpt-3.5-turbo

    key political and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.79
    URL
    -0.62
     violate
    -0.61
     simulate
    -0.60
    ĪĴ
    -0.59
    rame
    -0.58
    ģ«
    -0.58
    yrics
    -0.58
     traumatic
    -0.56
    rompt
    -0.55
    POSITIVE LOGITS
    !.
    0.76
    *.
    0.72
    .*
    0.69
     fame
    0.69
    ;
    0.68
    aceae
    0.67
    !
    0.65
    .
    0.64
     insofar
    0.64
    ione
    0.63
    Activations Density 0.406%

    No Known Activations