© 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. 3-RES-JB
    11. 64
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences expressing excitement or anticipation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adr
    -0.70
    mine
    -0.68
     dated
    -0.67
    avis
    -0.67
     mater
    -0.64
     diverted
    -0.62
    ford
    -0.62
     smuggled
    -0.61
    harm
    -0.61
    ãĥĥãĥī
    -0.61
    POSITIVE LOGITS
     anticipation
    0.78
     excited
    0.77
    roud
    0.75
    GGGGGGGG
    0.74
    mble
    0.72
    NESS
    0.71
    ULAR
    0.70
    vier
    0.70
     crowds
    0.69
     excitement
    0.69
    Activations Density 0.021%

    No Known Activations