© 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. 10-RES-JB
    11. 7793
    Prev
    Next
    INDEX
    Explanations

    descriptions of motion or rotation in a scientific context

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to physics and celestial mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nsics
    -0.92
     PTSD
    -0.81
    pkg
    -0.81
     Brands
    -0.78
     confession
    -0.77
     Priv
    -0.76
     Katz
    -0.75
     confessions
    -0.73
    onym
    -0.73
     Laboratories
    -0.73
    POSITIVE LOGITS
     oscill
    1.41
     rotating
    1.40
     rotate
    1.31
     perpendicular
    1.30
     rotation
    1.30
     ellipt
    1.28
     gravitational
    1.26
     velocity
    1.24
     orbits
    1.23
     spinning
    1.21
    Activations Density 0.445%

    No Known Activations