© 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. 20636
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotions or intense reactions, especially those related to bursting or erupting

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving intense emotional or physical 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
    saf
    -0.88
    heastern
    -0.78
    »Ĵ
    -0.75
    alty
    -0.69
    standard
    -0.69
     Borders
    -0.68
    taker
    -0.66
    imer
    -0.66
    TRY
    -0.65
     defic
    -0.64
    POSITIVE LOGITS
     excitement
    1.39
     laughter
    1.36
     adrenaline
    1.34
     fury
    1.25
     ecstasy
    1.21
     indignation
    1.18
     rage
    1.15
     applause
    1.14
     emotion
    1.14
     enthusiasm
    1.13
    Activations Density 0.192%

    No Known Activations