© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20937
    Prev
    Next
    INDEX
    Explanations

    adjectives expressing confusion, frustration, or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    emotional responses related to confusion or frustration

    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
     waivers
    -0.66
     bye
    -0.64
     deviations
    -0.63
     GP
    -0.62
    llan
    -0.59
     Policies
    -0.58
     approved
    -0.57
    payers
    -0.57
    eatures
    -0.57
     rule
    -0.57
    POSITIVE LOGITS
    ingly
    1.60
    ating
    0.99
    eful
    0.98
    ening
    0.96
    ifying
    0.92
    enment
    0.89
    ruciating
    0.89
    ing
    0.88
    risome
    0.86
    esc
    0.85
    Activations Density 0.084%

    No Known Activations