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. 14368
    Prev
    Next
    INDEX
    Explanations

    years, specifically the year 1917

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 1917 and its significance in historical contexts

    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
    DEV
    -0.71
    Ju
    -0.69
     Cruise
    -0.65
    chi
    -0.62
     Dragon
    -0.61
     junk
    -0.61
    DM
    -0.60
    ega
    -0.60
    Mod
    -0.60
     Damon
    -0.59
    POSITIVE LOGITS
     1917
    3.36
     1916
    3.27
     1914
    3.15
     1915
    3.07
     1918
    2.98
     1919
    2.66
     1913
    2.65
     1912
    2.54
     1905
    2.29
     1909
    2.29
    Activations Density 0.029%

    No Known Activations