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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14927
    Prev
    Next
    INDEX
    Explanations

    numerical quantities or rankings

    oai_token-act-pair · gpt-3.5-turbo

    nouns and significant entities related to various topics and issues

    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
    nature
    -0.60
    aution
    -0.60
     Roses
    -0.60
     Ara
    -0.60
    aeda
    -0.58
     Parties
    -0.58
     Facilities
    -0.58
     surpr
    -0.58
     compositions
    -0.57
     Arrows
    -0.57
    POSITIVE LOGITS
     apiece
    0.92
     per
    0.78
    secut
    0.72
     ounce
    0.68
    undred
    0.66
    inkle
    0.65
    iott
    0.64
     staffer
    0.64
    hander
    0.63
     summed
    0.63
    Activations Density 0.215%

    No Known Activations