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. 10-RES-JB
    6. 21089
    Prev
    Next
    INDEX
    Explanations

    astronomical terms or related concepts

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to astronomy and astronomical topics

    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
    idation
    -0.77
    iability
    -0.73
    idated
    -0.70
     Luxem
    -0.68
    idas
    -0.67
    POR
    -0.66
    Interstitial
    -0.65
    PLA
    -0.65
     Adidas
    -0.64
    fen
    -0.64
    POSITIVE LOGITS
     astronomers
    1.23
     telescope
    1.16
     astronomer
    1.14
     Telescope
    1.11
    omical
    1.08
     telescopes
    1.06
     astroph
    1.00
    autical
    0.98
    omy
    0.97
     Astron
    0.96
    Activations Density 0.043%

    No Known Activations