© 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. 9-RES-JB
    11. 10163
    Prev
    Next
    INDEX
    Explanations

    keywords found at the beginning of lists of items or points to follow in a document

    oai_token-act-pair · gpt-3.5-turbo

    sections that emphasize a list or description format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥı
    -0.72
    ËĪ
    -0.67
    orno
    -0.63
    nih
    -0.62
    natureconservancy
    -0.61
    urg
    -0.60
    isner
    -0.58
    driving
    -0.58
     fri
    -0.58
    angering
    -0.58
    POSITIVE LOGITS
     Thumbnails
    0.90
     summarizes
    0.86
     depicts
    0.84
    allery
    0.82
    neath
    0.80
     charts
    0.80
     screenshots
    0.80
     screenshot
    0.79
    above
    0.78
     tables
    0.78
    Activations Density 0.042%

    No Known Activations