© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 18692
    Prev
    Next
    INDEX
    Explanations

    financial amounts or values in the text

    oai_token-act-pair · gpt-3.5-turbo

    monetary figures in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Isle
    -0.82
     Charlottesville
    -0.74
     Daytona
    -0.70
     Hitman
    -0.66
     Hunts
    -0.66
    furt
    -0.66
     Antioch
    -0.65
     Beard
    -0.65
    beard
    -0.64
     Lindsey
    -0.64
    POSITIVE LOGITS
     crore
    1.82
     lakh
    1.52
     Rs
    1.16
    cro
    1.04
     cro
    1.00
     pa
    0.87
     ru
    0.86
     à¤
    0.85
    à¤
    0.80
    ा
    0.78
    Activations Density 0.043%

    No Known Activations