© 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. 7-RES-JB
    11. 2181
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific theories, particularly those proposed by renowned scientists

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terminology related to theoretical physics, specifically Einstein's theories of relativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FSA
    -0.84
    swick
    -0.79
     frontline
    -0.78
    Interstitial
    -0.76
    Veter
    -0.74
     Beir
    -0.74
     UNCLASSIFIED
    -0.71
     Veteran
    -0.71
     Leban
    -0.70
     curfew
    -0.70
    POSITIVE LOGITS
     theorem
    1.39
     mathematical
    1.31
     relativity
    1.24
     mathematic
    1.24
     physicists
    1.24
     equations
    1.23
     Mathemat
    1.22
     mathematician
    1.21
     theory
    1.16
     Theory
    1.16
    Activations Density 0.817%

    No Known Activations