© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3418
    Prev
    Next
    INDEX
    Explanations

    instances where the document mentions how something makes the person feel

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and emotional reactions

    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
    foreseen
    -0.71
    tesy
    -0.66
    accompan
    -0.63
    EngineDebug
    -0.63
     occurring
    -0.63
     curated
    -0.62
     Foss
    -0.61
    ibrary
    -0.61
     oversight
    -0.60
    etting
    -0.58
    POSITIVE LOGITS
     realize
    1.18
     feel
    1.17
     realise
    1.15
     jealous
    1.08
     rethink
    1.08
     happier
    1.06
     cringe
    1.05
     ashamed
    1.03
     laugh
    1.03
     aware
    1.01
    Activations Density 0.068%

    No Known Activations