© 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. 9-RES-JB
    11. 7176
    Prev
    Next
    INDEX
    Explanations

    references to numerical quantities of two or pairs

    oai_token-act-pair · gpt-3.5-turbo

    instances of numeric references or quantifications

    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
    ¬¼
    -0.83
    inventoryQuantity
    -0.76
    enture
    -0.69
    cffffcc
    -0.68
    natureconservancy
    -0.68
    soType
    -0.68
    ota
    -0.67
    ļ
    -0.67
    =~
    -0.67
    endo
    -0.66
    POSITIVE LOGITS
     namely
    1.31
     apiece
    1.17
     totaling
    1.16
     viz
    1.07
    two
    1.03
    each
    1.00
    one
    0.90
    three
    0.88
     consecut
    0.87
     respectively
    0.87
    Activations Density 0.425%

    No Known Activations