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. 8-RES-JB
    6. 5400
    Prev
    Next
    INDEX
    Explanations

    mentions of physical injuries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of injuries in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zees
    -0.77
    avanaugh
    -0.75
    zee
    -0.74
    rows
    -0.73
    eton
    -0.71
     Cosponsors
    -0.70
    perm
    -0.69
    rified
    -0.69
    nom
    -0.68
    zanne
    -0.67
    POSITIVE LOGITS
     inflicted
    0.90
     injury
    0.90
     sidelined
    0.89
     sustained
    0.88
     plagued
    0.87
     Injury
    0.84
     riddled
    0.82
     suspensions
    0.80
     suffered
    0.80
     replacements
    0.80
    Activations Density 0.036%

    No Known Activations