© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 12282
    Prev
    Next
    INDEX
    Explanations

    mentions of celestial bodies and planetary characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to celestial bodies and planetary discoveries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wireless
    -0.83
    verbal
    -0.76
    conn
    -0.76
    weeney
    -0.75
     fencing
    -0.74
    inelli
    -0.74
    apon
    -0.73
    cade
    -0.73
    isine
    -0.72
    upuncture
    -0.72
    POSITIVE LOGITS
     Jupiter
    1.84
     planets
    1.69
     orbits
    1.69
     moons
    1.65
     Pluto
    1.57
     Saturn
    1.57
     habitable
    1.57
     Neptune
    1.53
     orbiting
    1.52
    oplan
    1.43
    Activations Density 0.215%

    No Known Activations