Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 1152
    Prev
    Next
    INDEX
    Explanations

    mentions of "satellites"

    oai_token-act-pair · gpt-3.5-turbo

    references to satellites and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.92
    utenberg
    -0.74
    Style
    -0.73
    tm
    -0.72
    Gaming
    -0.70
     Snyder
    -0.70
    Production
    -0.69
     traumatic
    -0.69
    Man
    -0.69
    Woman
    -0.69
    POSITIVE LOGITS
     satellites
    1.41
     orbiting
    1.14
     satell
    1.03
     Seym
    0.93
     obser
    0.91
     galaxies
    0.89
     antennas
    0.86
     satellite
    0.84
     orbit
    0.83
     orbits
    0.82
    Activations Density 0.007%

    No Known Activations