© 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. 1-RES-JB
    11. 20436
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial matters or finance committees

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Finance" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    76561
    -0.82
     Cursed
    -0.73
     Twain
    -0.68
    upon
    -0.68
    imus
    -0.66
    gom
    -0.65
    avering
    -0.65
     Ange
    -0.64
     Dare
    -0.63
     Kore
    -0.60
    POSITIVE LOGITS
     Finance
    1.02
    iture
    0.87
    ahime
    0.81
     mathemat
    0.81
    ancing
    0.73
    folios
    0.73
     modelling
    0.73
     finance
    0.72
    omics
    0.71
    woman
    0.70
    Activations Density 0.004%

    No Known Activations