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. 9-RES-JB
    6. 4007
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports injuries, especially focusing on specific body parts like ACL tears and hamstring injuries

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports injuries, particularly those involving the ACL and hamstring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.78
    ween
    -0.76
     Cosponsors
    -0.76
    soDeliveryDate
    -0.74
     Objects
    -0.72
    eworld
    -0.71
    istas
    -0.70
    zanne
    -0.70
    cash
    -0.70
    galitarian
    -0.70
    POSITIVE LOGITS
     tendon
    1.49
     injury
    1.27
     lig
    1.15
     surgery
    1.15
     rehab
    1.12
     injuries
    1.09
     ankle
    1.07
     Surgery
    1.05
     ACL
    1.04
     Injury
    1.04
    Activations Density 0.086%

    No Known Activations