© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 17088
    Prev
    Next
    INDEX
    Explanations

    keywords related to nuclear reactors and incidents involving reactors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nuclear reactors and incidents involving them

    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
    boxing
    -0.77
    ãĤĭ
    -0.74
    haw
    -0.73
    lihood
    -0.70
     Merrill
    -0.70
     Agric
    -0.69
    umbnail
    -0.68
     AUD
    -0.67
    words
    -0.65
    alan
    -0.65
    POSITIVE LOGITS
     reactor
    1.00
     reactors
    0.99
     towers
    0.78
    ptions
    0.77
    uclear
    0.76
     coils
    0.74
     irrad
    0.74
     modernization
    0.73
     accidents
    0.72
     dismant
    0.72
    Activations Density 0.037%

    No Known Activations