© 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. 16076
    Prev
    Next
    INDEX
    Explanations

    terms related to theoretical physics, specifically focusing on Einstein's theories of relativity

    oai_token-act-pair · gpt-3.5-turbo

    references to Einstein's theories and related scientific concepts

    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
    ieft
    -0.79
    Saudi
    -0.75
    Veter
    -0.75
     branding
    -0.71
    rero
    -0.71
    erey
    -0.70
    porate
    -0.70
    anamo
    -0.70
    tips
    -0.69
     Somali
    -0.69
    POSITIVE LOGITS
     quantum
    1.43
     universes
    1.37
     physicists
    1.37
     atoms
    1.36
     relativity
    1.36
     physics
    1.35
     entropy
    1.35
     universe
    1.35
     gravitational
    1.34
     particle
    1.29
    Activations Density 0.860%

    No Known Activations