© 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. 8-RES-JB
    11. 11267
    Prev
    Next
    INDEX
    Explanations

    instances of commanding actions in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, specifically commas, in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yon
    -0.78
    mite
    -0.75
    umen
    -0.72
    rament
    -0.70
    odes
    -0.69
    ½
    -0.65
    omal
    -0.65
    nex
    -0.61
    iny
    -0.61
    cor
    -0.61
    POSITIVE LOGITS
     lest
    1.12
     but
    1.06
     although
    1.04
     prompting
    0.95
     fearing
    0.95
     whereas
    0.95
     namely
    0.93
     hoping
    0.91
     preferably
    0.90
     luckily
    0.90
    Activations Density 0.376%

    No Known Activations