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. 2-RES-JB
    6. 19252
    Prev
    Next
    INDEX
    Explanations

    words related to weight classes in boxing or martial arts

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific weight class in combat sports, particularly involving the term "welterweight."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.78
     CPC
    -0.78
     Gravity
    -0.73
     Scientist
    -0.70
     Grayson
    -0.70
     Medals
    -0.69
     Gab
    -0.69
     Merrill
    -0.68
     Teacher
    -0.68
     Normandy
    -0.68
    POSITIVE LOGITS
     wel
    1.14
    nut
    1.05
    tering
    1.00
    keye
    0.93
    nuts
    0.91
    ter
    0.86
    TERN
    0.84
    mount
    0.83
    terness
    0.83
    esh
    0.82
    Activations Density 0.005%

    No Known Activations