© 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. 11-RES-JB
    11. 20591
    Prev
    Next
    INDEX
    Explanations

    phrases expressing anticipation or curiosity towards future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing curiosity or interest about observations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ById
    -0.75
     disappeared
    -0.69
     disappearing
    -0.68
     retracted
    -0.65
     quitting
    -0.65
     waived
    -0.64
     vanished
    -0.64
     cance
    -0.63
     resignation
    -0.63
    selves
    -0.63
    POSITIVE LOGITS
     see
    1.38
     hear
    1.28
     speculate
    1.23
     revisit
    1.21
     explore
    1.19
     examine
    1.17
     compare
    1.14
     ponder
    1.14
     learn
    1.14
     observe
    1.11
    Activations Density 0.140%

    No Known Activations