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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16564
    Prev
    Next
    INDEX
    Explanations

    organizations and movements related to LGBTQ+ rights

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to LGBTQ+ advocacy and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xiety
    -0.61
    ©¶æ
    -0.52
    atre
    -0.51
    afety
    -0.51
     Azerbaijan
    -0.50
     Sagan
    -0.50
     PRESS
    -0.49
     Vance
    -0.49
     FEMA
    -0.49
     Gors
    -0.49
    POSITIVE LOGITS
    ipop
    0.63
     todd
    0.61
    jri
    0.60
    kefeller
    0.60
    ioch
    0.59
    iator
    0.57
     tert
    0.55
     predec
    0.54
    iates
    0.53
    ividual
    0.52
    Activations Density 1.981%

    No Known Activations