© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 721
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "with" and associated emotional descriptors

    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
    zman
    -0.71
    etary
    -0.71
    pton
    -0.61
     Featured
    -0.59
    sylvania
    -0.58
    ICS
    -0.58
     Related
    -0.58
     CLS
    -0.57
    Alternative
    -0.57
    estate
    -0.57
    POSITIVE LOGITS
     utmost
    1.28
     gust
    1.21
     pride
    1.17
     envy
    1.10
     aston
    1.09
     reverence
    1.09
     disdain
    1.08
     amaz
    1.08
     disgust
    1.07
     gratitude
    1.07
    Activations Density 0.088%

    No Known Activations