© 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. 6294
    Prev
    Next
    INDEX
    Explanations

    descriptions of astronomical phenomena

    oai_token-act-pair · gpt-3.5-turbo

    scientific terms and concepts related to astronomy and astrophysics

    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
     Homeless
    -0.89
    è»
    -0.82
     toile
    -0.79
    åĭ
    -0.77
    æ©
    -0.77
    ļéĨĴ
    -0.76
    uyomi
    -0.76
    ilet
    -0.75
     Criminal
    -0.74
    street
    -0.73
    POSITIVE LOGITS
     orbiting
    1.12
     astronomers
    1.10
     simulations
    0.99
     physicists
    0.98
     galaxies
    0.97
     rays
    0.95
     interstellar
    0.93
     satellites
    0.92
     whale
    0.88
     telescopes
    0.88
    Activations Density 0.309%

    No Known Activations