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. 19471
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical injuries and medical emergencies

    oai_token-act-pair · gpt-3.5-turbo

    instances of severe injury or life-threatening situations

    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
    allery
    -0.85
    Mods
    -0.77
    idth
    -0.73
    omi
    -0.73
    icion
    -0.72
    thren
    -0.70
    deals
    -0.68
     Answer
    -0.68
    isSpecialOrderable
    -0.67
     Gutenberg
    -0.66
    POSITIVE LOGITS
     unconscious
    1.64
     bleeding
    1.53
     hospitalized
    1.51
     paralyzed
    1.45
     injured
    1.39
     incapac
    1.36
     vomiting
    1.36
     dehyd
    1.33
     bruised
    1.31
     wounded
    1.30
    Activations Density 0.220%

    No Known Activations