© 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. 10-RES-JB
    11. 3204
    Prev
    Next
    INDEX
    Explanations

    words related to astronomy and celestial bodies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to celestial bodies and astronomical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urat
    -0.94
    hered
    -0.91
    edin
    -0.90
    chens
    -0.90
    aido
    -0.88
    yre
    -0.86
    Downloadha
    -0.84
    anu
    -0.84
    enment
    -0.83
    edited
    -0.81
    POSITIVE LOGITS
    ities
    1.03
    ity
    1.01
     mammals
    0.91
     mammal
    0.90
     anomalies
    0.85
     debris
    0.84
     ozone
    0.84
    ized
    0.84
     landmarks
    0.83
     aber
    0.83
    Activations Density 0.083%

    No Known Activations