© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 20723
    Prev
    Next
    INDEX
    Explanations

    information related to celestial bodies and astronomical phenomena, such as orbiting the sun and planetary movement

    oai_token-act-pair · gpt-3.5-turbo

    references to celestial bodies and their movements in relation to the sun

    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
    ilitary
    -0.73
    olicy
    -0.72
    isSpecialOrderable
    -0.71
    terness
    -0.69
    restling
    -0.67
    Training
    -0.67
    CVE
    -0.66
    ebook
    -0.65
    byter
    -0.65
    iltration
    -0.64
    POSITIVE LOGITS
     Milky
    1.55
     cosmos
    1.46
     Earth
    1.35
     planet
    1.34
     universe
    1.33
     Moon
    1.30
     Universe
    1.29
     moon
    1.28
     sun
    1.27
     heavens
    1.21
    Activations Density 0.141%

    No Known Activations