© 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. 3313
    Prev
    Next
    INDEX
    Explanations

    dates and events related to space missions

    oai_token-act-pair · gpt-3.5-turbo

    historical data and significant events related to space missions

    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
     Estate
    -0.91
     Ethnic
    -0.88
    law
    -0.86
     Restaur
    -0.86
     Anarch
    -0.82
    acist
    -0.81
     Taxes
    -0.81
     Lawyers
    -0.80
     thug
    -0.80
     Tavern
    -0.79
    POSITIVE LOGITS
     spacecraft
    1.51
     astronauts
    1.40
     orbiting
    1.40
     satellites
    1.36
     NASA
    1.33
    NASA
    1.33
     orbit
    1.33
     aboard
    1.29
     orbital
    1.27
     refuel
    1.24
    Activations Density 0.563%

    No Known Activations