© 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. 21005
    Prev
    Next
    INDEX
    Explanations

    words related to being worried, troubled, or having a strong interest in something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern or worry

    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
    arb
    -0.78
    iller
    -0.72
    aro
    -0.70
    orge
    -0.70
    avour
    -0.67
    hement
    -0.65
    ples
    -0.64
    exc
    -0.61
    urus
    -0.61
    avorite
    -0.61
    POSITIVE LOGITS
     about
    1.34
     ABOUT
    1.15
    about
    0.99
     lest
    0.97
     About
    0.96
    lessly
    0.96
    ingly
    0.95
     aloud
    0.86
     regarding
    0.82
    About
    0.81
    Activations Density 0.062%

    No Known Activations