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. 24229
    Prev
    Next
    INDEX
    Explanations

    references to Islamic extremist groups or military actions.

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific groups or factions in a conflict context

    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
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.70
     Edison
    -0.69
     Scotch
    -0.68
    Minecraft
    -0.67
    elong
    -0.66
     PAX
    -0.65
    iker
    -0.64
    ipeg
    -0.64
     Debt
    -0.63
     Robo
    -0.62
    POSITIVE LOGITS
    usra
    1.03
    Nusra
    0.93
     Front
    0.91
     Idlib
    0.87
    Syrian
    0.86
     rebels
    0.86
     fighters
    0.83
    Sham
    0.83
     fronts
    0.79
     Aleppo
    0.77
    Activations Density 0.023%

    No Known Activations