© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 8342
    Prev
    Next
    INDEX
    Explanations

    keywords related to income and taxes

    oai_token-act-pair · gpt-3.5-turbo

    references to income and financial measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingers
    -0.73
    olog
    -0.72
     Rabb
    -0.69
    witch
    -0.68
    ñ
    -0.65
     Snape
    -0.64
    yy
    -0.64
     Misty
    -0.64
     Shake
    -0.63
    cock
    -0.63
    POSITIVE LOGITS
     income
    3.54
     Income
    2.93
     incomes
    2.53
    income
    2.33
     earnings
    2.03
     revenue
    1.74
     salary
    1.56
     earners
    1.54
     revenues
    1.53
     wage
    1.51
    Activations Density 0.016%

    No Known Activations