© 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. 3-RES-JB
    11. 13294
    Prev
    Next
    INDEX
    Explanations

    phrases related to the abstract concept of "nature."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "nature" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rons
    -0.78
    ron
    -0.77
    kers
    -0.72
     Sutherland
    -0.70
    oned
    -0.68
    oning
    -0.67
    rom
    -0.66
    rican
    -0.66
    itone
    -0.66
    nuts
    -0.66
    POSITIVE LOGITS
     nature
    0.82
    uality
    0.80
     instinct
    0.70
     preserves
    0.69
     incarn
    0.69
    entially
    0.65
     disposition
    0.65
     Jiu
    0.63
     advers
    0.63
     Deity
    0.62
    Activations Density 0.009%

    No Known Activations