© 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. 2-RES-JB
    11. 17504
    Prev
    Next
    INDEX
    Explanations

    words indicating confusion or being puzzled

    oai_token-act-pair · gpt-3.5-turbo

    terms related to confusion or puzzlement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amins
    -0.80
    igers
    -0.72
    roleum
    -0.69
    mens
    -0.63
    llan
    -0.63
    rio
    -0.63
    umption
    -0.63
     credits
    -0.62
    ppo
    -0.62
    ods
    -0.61
    POSITIVE LOGITS
     baff
    1.21
     baffled
    1.15
     perplex
    1.10
     Puzz
    1.04
    ingly
    1.03
     bewild
    0.95
     vex
    0.92
     puzz
    0.91
     puzzled
    0.89
     puzzling
    0.86
    Activations Density 0.025%

    No Known Activations