© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1-RES-JB
    11. 21713
    Prev
    Next
    INDEX
    Explanations

    the word "nowadays."

    oai_token-act-pair · gpt-3.5-turbo

    references to contemporary themes or societal critiques

    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
    DCS
    -0.72
     Sands
    -0.70
    jar
    -0.65
    Mary
    -0.64
    ingham
    -0.62
     Betsy
    -0.61
    Topics
    -0.61
     Continued
    -0.60
    potion
    -0.60
    Dream
    -0.60
    POSITIVE LOGITS
    adays
    1.25
     nowadays
    1.23
     antioxid
    1.00
    entimes
    0.89
     occas
    0.85
    £ı
    0.81
    etheless
    0.81
    creen
    0.78
    days
    0.78
     compr
    0.74
    Activations Density 0.005%

    No Known Activations