© 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 EvalsExportsinterp-engineNEWAPI 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. 7-RES-JB
    11. 1881
    Prev
    Next
    INDEX
    Explanations

    keywords related to scientific theories, especially focusing on the word 'theory' itself

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mous
    -0.74
    ments
    -0.71
     Pradesh
    -0.69
     Ago
    -0.63
     Bold
    -0.62
    ovo
    -0.61
    iences
    -0.60
    Delivery
    -0.60
    events
    -0.59
     pledged
    -0.58
    POSITIVE LOGITS
    ologies
    0.99
    icist
    0.97
    craft
    0.87
    sonian
    0.82
     underpin
    0.80
     theories
    0.77
    peak
    0.76
    oult
    0.75
     theory
    0.75
     physicist
    0.74
    Activations Density 0.038%

    No Known Activations