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. 10-RES-JB
    6. 14623
    Prev
    Next
    INDEX
    Explanations

    sentences starting with the word "The"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "The" in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.79
    Elsewhere
    -0.66
     anew
    -0.65
    storm
    -0.63
    ously
    -0.62
    ibus
    -0.62
    rade
    -0.62
    inth
    -0.61
    inel
    -0.61
    igroup
    -0.61
    POSITIVE LOGITS
     simplest
    1.40
     easiest
    1.35
     quickest
    1.19
     safest
    1.17
    oret
    1.15
     slightest
    1.04
     majority
    1.04
     downside
    1.03
     basics
    1.02
     hardest
    1.01
    Activations Density 0.368%

    No Known Activations