© 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. 1-RES-JB
    11. 617
    Prev
    Next
    INDEX
    Explanations

    dates or time periods represented in four-digit numbers

    oai_token-act-pair · gpt-3.5-turbo

    specific years, particularly in the 19th century

    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
    ende
    -0.81
    kell
    -0.76
    etitive
    -0.75
    abol
    -0.75
    gotten
    -0.75
    RAM
    -0.75
    utils
    -0.73
    Choice
    -0.72
    pron
    -0.72
    env
    -0.72
    POSITIVE LOGITS
     1905
    1.12
     1890
    1.08
     1909
    1.07
     1906
    1.06
     1863
    1.03
     1908
    1.02
     1903
    1.01
     1862
    1.01
     1904
    1.00
     1870
    0.99
    Activations Density 0.009%

    No Known Activations