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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20229
    Prev
    Next
    INDEX
    Explanations

    descriptions or statements starting with the word "So"

    oai_token-act-pair · gpt-3.5-turbo

    the word "So" as a discourse marker indicating a shift or continuation in conversation

    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
    "},"
    -0.67
    "],"
    -0.62
    taboola
    -0.61
    capt
    -0.60
     portfolio
    -0.58
    blind
    -0.58
    wreck
    -0.58
    guard
    -0.58
    weights
    -0.57
     UCHIJ
    -0.57
    POSITIVE LOGITS
    ften
    1.07
    fter
    1.05
     yeah
    1.04
    oooo
    1.04
    ooo
    1.04
    oner
    1.02
    aring
    1.02
    apy
    0.94
     glad
    0.94
     far
    0.90
    Activations Density 0.061%

    No Known Activations