© 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. 6-RES-JB
    11. 2976
    Prev
    Next
    INDEX
    Explanations

    specific patterns representing numerical ranges, particularly those following a hyphen

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of hyphenated phrases and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rica
    -0.83
     Shades
    -0.75
     Reviews
    -0.69
     Lanka
    -0.67
     Nights
    -0.65
     Cry
    -0.64
     dances
    -0.64
     Dice
    -0.62
     IX
    -0.62
     Reflect
    -0.61
    POSITIVE LOGITS
    same
    0.92
    largest
    0.91
    headed
    0.90
    named
    0.90
    liest
    0.89
    powered
    0.87
    deb
    0.87
    equ
    0.87
    haired
    0.86
    awaited
    0.86
    Activations Density 0.189%

    No Known Activations