© 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. 8591
    Prev
    Next
    INDEX
    Explanations

    instances where the writer expresses a desire or longing for something

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "would love to" and its variations

    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
    orno
    -0.79
     Ariel
    -0.71
    ively
    -0.71
     Worth
    -0.70
     Ascension
    -0.67
    furt
    -0.65
    ById
    -0.62
    grounds
    -0.61
     Ori
    -0.60
     Lauder
    -0.60
    POSITIVE LOGITS
     hear
    1.39
     see
    1.36
     emulate
    1.01
     find
    1.01
     know
    1.00
     revisit
    0.98
     receive
    0.97
     learn
    0.95
     someday
    0.93
     collaborate
    0.91
    Activations Density 0.082%

    No Known Activations