© 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. 1343
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "ambush"

    oai_token-act-pair · gpt-3.5-turbo

    variants of the word "ambient."

    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
    creen
    -0.68
     learners
    -0.62
     Gutenberg
    -0.59
     MFT
    -0.58
     Ti
    -0.58
     Copyright
    -0.57
     evapor
    -0.56
    ãĥīãĥ©ãĤ´ãĥ³
    -0.56
     learning
    -0.55
     miser
    -0.55
    POSITIVE LOGITS
    assadors
    1.58
    assad
    1.58
    iance
    1.42
    ivalent
    1.40
    assador
    1.35
    iguous
    1.35
    ushed
    1.31
    ience
    1.29
    ulatory
    1.25
    ushes
    1.18
    Activations Density 0.033%

    No Known Activations