© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 12372
    Prev
    Next
    INDEX
    Explanations

    descriptions of astronomical phenomena and celestial bodies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to astrophysical phenomena and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è»
    -0.93
    ãĥ©ãĥ³
    -0.83
    ħĭ
    -0.79
     veter
    -0.79
     guiIcon
    -0.78
    åĭ
    -0.78
    uyomi
    -0.77
    ãĤ¨ãĥ«
    -0.77
    é¾įå
    -0.77
    çͰ
    -0.76
    POSITIVE LOGITS
     orbiting
    1.02
     astronomers
    0.97
     simulations
    0.94
     hump
    0.86
     galaxies
    0.86
     telescopes
    0.82
     whales
    0.81
     habitable
    0.81
     physicists
    0.81
     satellites
    0.80
    Activations Density 0.222%

    No Known Activations