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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 15258
    Prev
    Next
    INDEX
    Explanations

    keywords related to time periods

    oai_token-act-pair · gpt-3.5-turbo

    temporal markers and references to historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    optional
    -0.69
    ãĤĮ
    -0.69
     ank
    -0.67
    ethyst
    -0.66
    hani
    -0.66
     pled
    -0.63
    ODY
    -0.63
    gallery
    -0.62
     deserving
    -0.62
    Ingredients
    -0.61
    POSITIVE LOGITS
     WWII
    1.45
     1945
    1.30
     WW
    1.21
     World
    1.20
     1917
    1.18
     colonialism
    1.18
     1948
    1.15
     Communism
    1.15
     communism
    1.12
     1914
    1.11
    Activations Density 0.334%

    No Known Activations