© 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. 4-RES-JB
    11. 7224
    Prev
    Next
    INDEX
    Explanations

    information related to nuclear reactors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of nuclear reactors and their statuses

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

    No Comments

    Negative Logits
    ean
    -0.72
     Beg
    -0.70
     Merrill
    -0.69
     Agric
    -0.68
    haw
    -0.68
    boxing
    -0.67
     Lives
    -0.67
     Hills
    -0.67
    ãĤĭ
    -0.66
    ilan
    -0.66
    POSITIVE LOGITS
     reactors
    1.11
     reactor
    1.10
    inery
    0.82
    ptions
    0.81
     coils
    0.78
    uclear
    0.77
     towers
    0.75
     dismant
    0.75
     installations
    0.75
     turrets
    0.74
    Activations Density 0.019%

    No Known Activations