© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 2426
    Prev
    Next
    INDEX
    Explanations

    words related to the concept or idea of "nature" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of '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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rons
    -0.82
    Interstitial
    -0.78
    rican
    -0.68
    Introduced
    -0.68
    ron
    -0.68
     Ezek
    -0.67
     Sutherland
    -0.65
     Stall
    -0.64
    oning
    -0.64
    window
    -0.64
    POSITIVE LOGITS
     nature
    1.06
    nature
    0.84
    uality
    0.83
    ivism
    0.77
    entially
    0.73
     unlaw
    0.71
     gravity
    0.69
    ativity
    0.69
    istries
    0.68
    ivist
    0.67
    Activations Density 0.008%

    No Known Activations