© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4873
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and business operations

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to financial transactions and related terms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     landlords
    -0.68
     places
    -0.65
     occasion
    -0.62
    Ö¼
    -0.59
     digging
    -0.58
    ucket
    -0.58
     onlook
    -0.57
     embr
    -0.56
     owning
    -0.56
    witch
    -0.56
    POSITIVE LOGITS
     quantities
    0.80
     payload
    0.77
    metadata
    0.76
    ãĤ¹ãĥĪ
    0.75
     batches
    0.74
     quantity
    0.73
    message
    0.71
     brunt
    0.70
     amounts
    0.70
    ãĥĨ
    0.68
    Activations Density 0.712%

    No Known Activations