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. 10-RES-JB
    6. 207
    Prev
    Next
    INDEX
    Explanations

    terms related to radiation in the context of disasters

    oai_token-act-pair · gpt-3.5-turbo

    references to radiation and its effects, specifically in relation to the Fukushima disaster

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eenth
    -0.85
    theless
    -0.75
    neys
    -0.75
    lier
    -0.74
    lihood
    -0.73
    liness
    -0.72
    aws
    -0.71
    thood
    -0.68
    ernaut
    -0.67
    pages
    -0.67
    POSITIVE LOGITS
     radiation
    1.16
     shielding
    1.14
     irrad
    1.10
     horm
    1.07
     iodine
    1.07
     detectors
    1.03
     sickness
    1.03
     isot
    1.01
     doses
    1.00
     emitted
    1.00
    Activations Density 0.042%

    No Known Activations