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. 11-RES-JB
    6. 17833
    Prev
    Next
    INDEX
    Explanations

    occurrences of medical emergencies and fatal incidents

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of violent incidents and medical emergencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Favor
    -0.77
     promotion
    -0.73
     sponsoring
    -0.71
     Influence
    -0.67
     endorsements
    -0.67
     promoting
    -0.66
    é¾įå¥ij士
    -0.66
    ahead
    -0.66
     recruiting
    -0.63
     Promotion
    -0.62
    POSITIVE LOGITS
     vom
    1.57
     suffered
    1.46
     collapsed
    1.41
     underwent
    1.33
     died
    1.33
     regained
    1.32
     awoke
    1.32
     succumbed
    1.31
     cried
    1.27
     screamed
    1.27
    Activations Density 0.305%

    No Known Activations