© 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. 8-RES-JB
    11. 22394
    Prev
    Next
    INDEX
    Explanations

    topics related to race and ethnicity

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to demographics and diversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shutterstock
    -0.69
     Budget
    -0.55
     creditors
    -0.55
     Auditor
    -0.54
     Profit
    -0.53
     chemotherapy
    -0.53
     lenders
    -0.53
     IMF
    -0.53
     Feminist
    -0.52
     Investors
    -0.52
    POSITIVE LOGITS
    initely
    0.68
    oooooooooooooooo
    0.63
    atural
    0.63
    ozyg
    0.63
    retty
    0.63
     indeed
    0.63
     resemb
    0.62
    avorite
    0.62
    irmed
    0.61
    ocally
    0.61
    Activations Density 1.626%

    No Known Activations