© 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. 15948
    Prev
    Next
    INDEX
    Explanations

    numerical quantities followed by nouns

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics related to quantities and counts

    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
    charge
    -0.76
    matter
    -0.76
    ighter
    -0.75
    bsite
    -0.72
    udeb
    -0.71
    à¥
    -0.71
    actionDate
    -0.70
    zzy
    -0.70
    earth
    -0.67
    ENSE
    -0.67
    POSITIVE LOGITS
     finalists
    1.09
     ways
    0.83
     contenders
    0.80
     remaining
    0.78
     quir
    0.77
     factors
    0.75
     reasons
    0.75
     siblings
    0.75
     choices
    0.72
     categories
    0.72
    Activations Density 0.084%

    No Known Activations