© 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. 2-RES-JB
    11. 22090
    Prev
    Next
    INDEX
    Explanations

    references to numerical quantities of a thousand

    oai_token-act-pair · gpt-3.5-turbo

    instances of the keyword "thousand."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imir
    -0.76
    foundation
    -0.71
    liga
    -0.66
    icipated
    -0.65
    raising
    -0.65
    shown
    -0.64
    league
    -0.64
    annel
    -0.62
     weakened
    -0.61
    stood
    -0.60
    POSITIVE LOGITS
     Thousand
    0.99
    aires
    0.98
     dollars
    0.96
     000
    0.95
     thousand
    0.94
     ILCS
    0.93
     miles
    0.90
    aire
    0.90
     Oaks
    0.86
    ousand
    0.86
    Activations Density 0.010%

    No Known Activations