© 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 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. 19989
    Prev
    Next
    INDEX
    Explanations

    reviews and writing activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of empty or missing text segments

    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
    Demand
    -0.67
    itiz
    -0.65
    Ultimately
    -0.63
    imeters
    -0.62
    Whoever
    -0.62
    thing
    -0.61
    pecting
    -0.60
    existent
    -0.59
    Eventually
    -0.58
     helicop
    -0.58
    POSITIVE LOGITS
     largeDownload
    0.95
     annot
    0.85
     transcript
    0.83
     overview
    0.80
     infographic
    0.78
     Introduction
    0.76
     excerpt
    0.76
     reprint
    0.76
     english
    0.75
     Transcript
    0.75
    Activations Density 0.440%

    No Known Activations