© 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. 6-RES-JB
    11. 1076
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe frequency or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that suggest frequency or likelihood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inea
    -0.83
    ves
    -0.74
    eer
    -0.74
    iry
    -0.74
    uese
    -0.73
    itivity
    -0.73
    utenberg
    -0.72
    vae
    -0.71
    leground
    -0.71
    atur
    -0.71
    POSITIVE LOGITS
     excluding
    1.00
     implying
    0.85
     adolesc
    0.83
     preferring
    0.82
     assuming
    0.82
     comprising
    0.81
    entimes
    0.80
     culminating
    0.78
     eliminating
    0.77
     mediated
    0.77
    Activations Density 0.139%

    No Known Activations