© 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. 11-RES-JB
    11. 21187
    Prev
    Next
    INDEX
    Explanations

    currency amounts in British pounds

    oai_token-act-pair · gpt-3.5-turbo

    references to amounts of money, especially in pounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jem
    -0.67
    culosis
    -0.64
    uddin
    -0.62
     Pru
    -0.62
     Boone
    -0.61
     historically
    -0.60
     brut
    -0.60
     Zub
    -0.60
     pige
    -0.59
     Pruitt
    -0.59
    POSITIVE LOGITS
    780
    0.92
    620
    0.91
    £
    0.91
    650
    0.90
    319
    0.88
    iOS
    0.87
    NZ
    0.87
    412
    0.87
    439
    0.86
    340
    0.86
    Activations Density 0.022%

    No Known Activations