© 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. 4-RES-JB
    11. 733
    Prev
    Next
    INDEX
    Explanations

    references to the International Space Station

    oai_token-act-pair · gpt-3.5-turbo

    mentions of space stations and related terminology

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

    No Comments

    Negative Logits
    é»Ĵ
    -0.79
     Styles
    -0.76
    sbm
    -0.76
    ãĤ±
    -0.75
    Viol
    -0.72
     Marketable
    -0.70
    values
    -0.67
    icia
    -0.65
    raud
    -0.65
    estamp
    -0.64
    POSITIVE LOGITS
     orbiting
    1.08
    arium
    0.93
     astronauts
    0.89
     docking
    0.84
     satellites
    0.75
     spacecraft
    0.75
    lift
    0.75
     Station
    0.74
    keeping
    0.73
     refuel
    0.73
    Activations Density 0.019%

    No Known Activations