© 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. 10-RES-JB
    11. 16658
    Prev
    Next
    INDEX
    Explanations

    words related to money, currency, and prices

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and currency symbols

    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
     Clifford
    -0.83
     Brendan
    -0.80
     Kerr
    -0.80
     corrections
    -0.77
     chord
    -0.76
     Jal
    -0.76
     Ezek
    -0.75
     Brig
    -0.73
     dermat
    -0.73
     offending
    -0.72
    POSITIVE LOGITS
    1500
    1.84
    1000
    1.78
     1500
    1.76
    2500
    1.73
     2500
    1.72
    1200
    1.71
     1000
    1.70
     3000
    1.67
     1200
    1.67
    2000
    1.63
    Activations Density 0.087%

    No Known Activations