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. 10-RES-JB
    6. 8778
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports injuries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sylv
    -0.75
    DragonMagazine
    -0.70
    oho
    -0.70
    istas
    -0.68
    cest
    -0.67
     Guides
    -0.66
    INTON
    -0.66
    isans
    -0.65
    izens
    -0.64
     Straw
    -0.64
    POSITIVE LOGITS
     injury
    1.67
     illness
    1.59
     injuries
    1.58
     concussion
    1.57
     hamstring
    1.53
     groin
    1.43
     ailments
    1.40
     Injury
    1.34
     pneumonia
    1.32
     tendon
    1.32
    Activations Density 0.223%

    No Known Activations