Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17843
    Prev
    Next
    INDEX
    Explanations

    terms related to social issues and communities, with a focus on marginalized groups and challenges such as disabilities and race

    oai_token-act-pair · gpt-3.5-turbo

    references to social and political issues related to minorities and injustices

    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
    lopp
    -0.71
    ilst
    -0.60
    Lat
    -0.59
    acre
    -0.58
    cies
    -0.56
    asma
    -0.55
     Anch
    -0.54
    gans
    -0.54
     Celebr
    -0.53
    atalie
    -0.53
    POSITIVE LOGITS
     obsolete
    0.94
     irrelevant
    0.93
     outweigh
    0.90
     squarely
    0.84
     moot
    0.82
     hostage
    0.81
     intact
    0.80
     contingent
    0.80
     intolerable
    0.80
     seriously
    0.78
    Activations Density 0.568%

    No Known Activations