© 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. 16043
    Prev
    Next
    INDEX
    Explanations

    the name "Sabine."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific name, likely indicating a key figure or entity in the text

    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
     Thumbnails
    -0.69
    WAYS
    -0.66
     expectancy
    -0.65
     Founders
    -0.64
     Scythe
    -0.64
     Borders
    -0.62
    SPONSORED
    -0.62
     fung
    -0.62
    overs
    -0.61
     Confederacy
    -0.61
    POSITIVE LOGITS
    rina
    1.28
    arat
    1.07
    ril
    1.01
    onis
    1.00
    rill
    0.99
    arin
    0.96
    aram
    0.94
    ella
    0.92
    qua
    0.91
    ulation
    0.91
    Activations Density 0.027%

    No Known Activations