© 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. 0-RES-JB
    11. 8202
    Prev
    Next
    INDEX
    Explanations

    references to celestial bodies, with a focus on the moon

    oai_token-act-pair · gpt-3.5-turbo

    references to lunar phenomena and eclipses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psc
    -0.76
    ierre
    -0.71
    words
    -0.71
     Butler
    -0.68
    Mich
    -0.66
    igans
    -0.65
    buff
    -0.65
     Tweet
    -0.65
    atoes
    -0.64
     Izzy
    -0.64
    POSITIVE LOGITS
     lunar
    3.83
     Lunar
    2.87
     eclipse
    1.97
     moon
    1.79
     Moon
    1.63
    Moon
    1.61
     Martian
    1.51
     Apollo
    1.43
     celestial
    1.40
     Planetary
    1.40
    Activations Density 0.027%

    No Known Activations