© 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. 0-RES-JB
    11. 5228
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the name "Newton"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Newton."

    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
     dues
    -0.71
     border
    -0.65
     embassy
    -0.65
    .#
    -0.64
     troll
    -0.64
     Horde
    -0.63
    Border
    -0.63
    pes
    -0.63
    Ser
    -0.63
     spo
    -0.62
    POSITIVE LOGITS
     Newton
    3.97
     Einstein
    1.44
     Galileo
    1.44
     Kelvin
    1.40
     Kepler
    1.26
     Bridgewater
    1.26
     Newtown
    1.21
     Locke
    1.20
     Newman
    1.16
     Edison
    1.10
    Activations Density 0.025%

    No Known Activations