© 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 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. 3-RES-JB
    11. 24416
    Prev
    Next
    INDEX
    Explanations

    median values in different contexts, such as taxes, earnings, and income

    oai_token-act-pair · gpt-3.5-turbo

    references to median statistics, particularly concerning income and property taxes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    choes
    -0.80
    Revolution
    -0.74
    obby
    -0.72
    matic
    -0.70
    velt
    -0.69
    YN
    -0.69
    IGHTS
    -0.68
    oyal
    -0.67
    uador
    -0.66
    CHQ
    -0.64
    POSITIVE LOGITS
     median
    0.93
     Median
    0.77
    ulla
    0.72
     responders
    0.69
    enhagen
    0.69
    itures
    0.67
     Income
    0.67
     responses
    0.65
    wealth
    0.65
     Flames
    0.64
    Activations Density 0.008%

    No Known Activations