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. 3-RES-JB
    6. 10845
    Prev
    Next
    INDEX
    Explanations

    words related to specific medical conditions affecting the lower body, such as hamstring, ACL, Achilles, and groin injuries

    oai_token-act-pair · gpt-3.5-turbo

    references to specific types of muscle and ligament injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advertising
    -0.74
    SPONSORED
    -0.71
    rers
    -0.71
    ahead
    -0.71
    UTC
    -0.70
    ship
    -0.69
    upt
    -0.68
    uscript
    -0.66
     Vide
    -0.64
    echo
    -0.64
    POSITIVE LOGITS
     tendon
    1.14
     hamstring
    1.01
     muscles
    0.98
     groin
    0.92
     injuries
    0.90
     shoulder
    0.90
     injury
    0.85
     ankle
    0.82
     joints
    0.81
    bone
    0.81
    Activations Density 0.012%

    No Known Activations