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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-RES-JB
    6. 3246
    Prev
    Next
    INDEX
    Explanations

    phrases related to celestial orbits

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of orbital paths for celestial bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cham
    -0.72
    ford
    -0.69
    Sharp
    -0.69
    asant
    -0.68
    jit
    -0.67
    ech
    -0.63
    crim
    -0.62
    erick
    -0.60
     Fowler
    -0.60
     Provincial
    -0.60
    POSITIVE LOGITS
     orbit
    4.19
     orbits
    2.74
     Orbit
    2.31
     orbital
    2.03
     orbiting
    1.91
    orbit
    1.57
     Orbital
    1.23
     satellites
    1.22
     gravitational
    1.19
     orb
    1.19
    Activations Density 0.012%

    No Known Activations