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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3266
    Prev
    Next
    INDEX
    Explanations

    words related to nuclear power plants and reactors

    oai_token-act-pair · gpt-3.5-turbo

    references to nuclear power plants and their reactors

    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
     Scholar
    -0.74
    ãģĦ
    -0.73
     Patterns
    -0.71
     Marketable
    -0.70
     Pieces
    -0.66
     Styles
    -0.65
     Person
    -0.64
    CHAT
    -0.64
     Gifts
    -0.63
     Languages
    -0.62
    POSITIVE LOGITS
     operator
    1.22
     operated
    1.17
     operators
    1.05
     pumping
    1.01
     wastewater
    0.97
     reactors
    0.96
     servicing
    0.94
     operating
    0.92
     construction
    0.92
     reactor
    0.92
    Activations Density 0.160%

    No Known Activations