© 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. 3-RES-JB
    11. 9389
    Prev
    Next
    INDEX
    Explanations

    references to celestial bodies, specifically the moon

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "moon" in relation to various contexts

    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
    ãĤ¢ãĥ«
    -0.80
    ÃĽ
    -0.78
     Flavoring
    -0.78
    elvet
    -0.78
    Sem
    -0.78
    Interstitial
    -0.77
    idents
    -0.77
    WER
    -0.76
    irrel
    -0.74
    utenberg
    -0.74
    POSITIVE LOGITS
     orbiting
    1.00
     moon
    0.99
    light
    0.98
    lit
    0.95
     eclipse
    0.92
    beam
    0.92
     rover
    0.89
     moons
    0.89
    stone
    0.86
    lighting
    0.82
    Activations Density 0.007%

    No Known Activations