Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15556
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate surprise or unexpectedness

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of surprise or unexpectedness

    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
    •layer 11 - surprise

    No Comments

    Negative Logits
    urance
    -0.74
    interstitial
    -0.66
    riage
    -0.65
    aneously
    -0.65
    ergy
    -0.65
    heit
    -0.65
     Accessed
    -0.65
    aneous
    -0.64
    athering
    -0.64
    vance
    -0.63
    POSITIVE LOGITS
     me
    1.38
     outsiders
    1.26
     anyone
    1.14
     us
    1.10
     observers
    1.08
     anybody
    1.08
     many
    1.07
     everyone
    0.98
     most
    0.98
     everybody
    0.94
    Activations Density 0.162%

    No Known Activations