© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11190
    Prev
    Next
    INDEX
    Explanations

    words related to confusion, perplexity, and bewilderment

    oai_token-act-pair · gpt-3.5-turbo

    words that express confusion or frustration

    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
     equity
    -0.68
     bye
    -0.67
     faire
    -0.65
     Policies
    -0.62
     subcontract
    -0.62
     Rover
    -0.62
     RL
    -0.61
     Order
    -0.61
     allowance
    -0.60
     approved
    -0.60
    POSITIVE LOGITS
    ingly
    1.58
    stru
    1.00
    ulous
    0.93
    ienced
    0.91
    ibly
    0.89
    ience
    0.88
    iously
    0.87
    ace
    0.87
    azes
    0.87
    ible
    0.87
    Activations Density 0.088%

    No Known Activations