Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24325
    Prev
    Next
    INDEX
    Explanations

    mentions of toxic substances or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to toxic substances and their effects on health and safety

    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
     Fellowship
    -0.66
    365
    -0.64
    gain
    -0.64
    zig
    -0.62
    ploma
    -0.60
     authenticated
    -0.60
     Advent
    -0.60
     triumphant
    -0.59
    Attack
    -0.58
    cision
    -0.57
    POSITIVE LOGITS
     substances
    1.23
    ology
    1.16
     fumes
    1.15
    ological
    1.15
    ologist
    1.11
     chemicals
    1.05
     gases
    1.04
    ologists
    1.03
     waste
    1.03
     algae
    0.97
    Activations Density 0.071%

    No Known Activations