© 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. 2349
    Prev
    Next
    INDEX
    Explanations

    financial numbers or amounts mentioned in a text

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

    numerical data related to monetary values or statistics

    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
     proble
    -0.80
     anat
    -0.76
     metic
    -0.75
     hop
    -0.74
     spont
    -0.73
     spor
    -0.71
     gut
    -0.71
     anatomy
    -0.71
     coping
    -0.70
     oversight
    -0.70
    POSITIVE LOGITS
    000
    1.67
    999
    1.57
    500
    1.57
    250
    1.55
    750
    1.54
    050
    1.51
    900
    1.44
    800
    1.43
    950
    1.43
    333
    1.43
    Activations Density 0.033%

    No Known Activations