Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16305
    Prev
    Next
    INDEX
    Explanations

    references to specific years in the 20th century

    oai_token-act-pair · gpt-3.5-turbo

    specific years mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orbital
    -0.67
    OD
    -0.66
    Ub
    -0.66
     cloud
    -0.64
     deployment
    -0.63
     chip
    -0.63
     iT
    -0.62
     Chris
    -0.62
     drone
    -0.62
     Meg
    -0.61
    POSITIVE LOGITS
     1923
    3.11
     1927
    3.09
     1924
    3.04
     1926
    3.04
     1925
    3.01
     1928
    2.99
     1929
    2.93
     1921
    2.89
     1931
    2.81
     1922
    2.80
    Activations Density 0.037%

    No Known Activations