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. 6-RES-JB
    6. 3849
    Prev
    Next
    INDEX
    Explanations

    information related to radiation levels, incidents, and effects

    oai_token-act-pair · gpt-3.5-turbo

    references to radiation levels and contamination, particularly associated with Fukushima

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eenth
    -0.88
    lihood
    -0.79
    ndra
    -0.77
    thood
    -0.75
    ths
    -0.74
    avanaugh
    -0.74
    lier
    -0.74
    neys
    -0.72
    ership
    -0.72
    lopp
    -0.72
    POSITIVE LOGITS
     radiation
    1.05
     emitted
    0.95
     detectors
    0.91
     sickness
    0.90
     belts
    0.89
     iodine
    0.88
     exposure
    0.88
     shielding
    0.88
     irrad
    0.87
     horm
    0.87
    Activations Density 0.024%

    No Known Activations