© 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
    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. 1339
    Prev
    Next
    INDEX
    Explanations

    the word "so" used to imply a certain action or consequence

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "to do so" in various contexts

    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
    resa
    -0.64
     Lau
    -0.64
    works
    -0.62
    ¢
    -0.58
     Swanson
    -0.58
    ãĥ¯ãĥ³
    -0.57
    land
    -0.56
     Sawyer
    -0.56
     Dre
    -0.55
     Wes
    -0.54
    POSITIVE LOGITS
    oner
    0.99
    othe
    0.90
    oths
    0.88
    iety
    0.86
     anonymously
    0.80
     responsibly
    0.79
    ront
    0.78
    uchin
    0.78
     forth
    0.78
     voluntarily
    0.77
    Activations Density 0.049%

    No Known Activations