© 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. 8-RES-JB
    11. 20433
    Prev
    Next
    INDEX
    Explanations

    words related to cosmic and galactic entities or phenomena

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cosmic phenomena and space-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iage
    -1.12
    iculture
    -0.98
    HCR
    -0.95
    abet
    -0.89
    lund
    -0.88
    ament
    -0.83
    usalem
    -0.79
    hip
    -0.79
    yrim
    -0.79
    ied
    -0.79
    POSITIVE LOGITS
     rays
    1.24
     ray
    1.03
     microwave
    0.88
     proportions
    0.73
     smoker
    0.69
     radiation
    0.69
     cosmic
    0.64
    orp
    0.64
     Radiation
    0.62
    enter
    0.62
    Activations Density 0.073%

    No Known Activations