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. 8-RES-JB
    6. 14646
    Prev
    Next
    INDEX
    Explanations

    mentions of groups or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "s" in the text

    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
     Pharaoh
    -0.64
     Tours
    -0.63
     Niet
    -0.62
     Hots
    -0.62
    PN
    -0.60
     Sets
    -0.60
     Gaul
    -0.60
     Amer
    -0.60
    ocent
    -0.60
    Compare
    -0.60
    POSITIVE LOGITS
    ELF
    1.22
     own
    1.03
     namesake
    1.01
    selves
    0.97
     mascot
    0.94
    niper
    0.85
    ullivan
    0.85
     logo
    0.84
    ources
    0.84
    keleton
    0.83
    Activations Density 0.134%

    No Known Activations