© 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. 3438
    Prev
    Next
    INDEX
    Explanations

    verbs of obligation or necessity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express necessity or obligation

    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
    furt
    -0.60
    hots
    -0.60
    Low
    -0.59
     Palest
    -0.58
     Chatt
    -0.58
     Laksh
    -0.58
    ī
    -0.57
    alyses
    -0.56
    arthed
    -0.55
    riad
    -0.54
    POSITIVE LOGITS
     admit
    1.32
     wonder
    1.15
     remember
    1.06
     reckon
    1.03
     admire
    1.02
     realize
    1.00
     respect
    1.00
     acknowledge
    1.00
     beware
    0.99
     concede
    0.98
    Activations Density 0.080%

    No Known Activations