© 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. 11794
    Prev
    Next
    INDEX
    Explanations

    phrases related to national and international civil space activities

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to space activities and programs

    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
    amaru
    -0.93
    acia
    -0.84
     fentanyl
    -0.82
     Geral
    -0.81
     compr
    -0.81
    leground
    -0.80
    monton
    -0.78
    aido
    -0.77
    ocard
    -0.76
    orkshire
    -0.76
    POSITIVE LOGITS
    NASA
    2.23
     NASA
    2.22
     astronauts
    2.10
     SpaceX
    2.05
     astronaut
    2.00
     spacecraft
    1.91
     Nasa
    1.83
     Planetary
    1.77
     Space
    1.76
     Astron
    1.73
    Activations Density 0.500%

    No Known Activations