© 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. 12617
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to societal issues and controversies, particularly involving health, relationships, and ethics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to marginalized or vulnerable groups in society

    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
    ptroller
    -0.93
    inventoryQuantity
    -0.81
    inator
    -0.78
    iggurat
    -0.76
    ologue
    -0.75
    forcer
    -0.74
    advertisement
    -0.74
    thora
    -0.73
    inatory
    -0.71
    ãĤ´ãĥ³
    -0.71
    POSITIVE LOGITS
     individuals
    1.58
     persons
    1.49
     people
    1.46
     males
    1.42
     adults
    1.41
     youths
    1.39
     couples
    1.36
     folks
    1.31
     Americans
    1.30
     men
    1.29
    Activations Density 0.258%

    No Known Activations