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. 10596
    Prev
    Next
    INDEX
    Explanations

    mentions of industrial plants, especially nuclear plants

    oai_token-act-pair · gpt-3.5-turbo

    references to industrial or manufacturing facilities, specifically plants

    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
    */(
    -0.95
    yip
    -0.89
    CHAT
    -0.87
    theless
    -0.80
    etheless
    -0.77
    dash
    -0.71
    laus
    -0.70
    BOOK
    -0.69
    ojure
    -0.65
    cffff
    -0.64
    POSITIVE LOGITS
     plants
    0.85
    inery
    0.83
     operator
    0.78
    ronics
    0.78
    places
    0.75
    rastructure
    0.73
     plant
    0.73
     âĵĺ
    0.72
     operators
    0.72
     accident
    0.71
    Activations Density 0.021%

    No Known Activations