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. 0-RES-JB
    6. 5867
    Prev
    Next
    INDEX
    Explanations

    phrases related to running marathons

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "marathon."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Element
    -0.72
    ENTS
    -0.70
     chips
    -0.70
    INGS
    -0.65
    âĸij
    -0.64
    )=(
    -0.64
    Chip
    -0.64
    ament
    -0.64
     Chips
    -0.62
    ibles
    -0.62
    POSITIVE LOGITS
     marathon
    3.74
     Marathon
    3.41
    athon
    1.90
    athlon
    1.53
     runners
    1.34
     treadmill
    1.09
     Olympics
    1.04
    runner
    1.02
     jog
    1.00
     runner
    0.97
    Activations Density 0.014%

    No Known Activations