© 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. 8-RES-JB
    11. 1068
    Prev
    Next
    INDEX
    Explanations

    numerical and statistical information related to different topics including economics, demographics, and technology

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to economic or demographic trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dilig
    -0.66
    farious
    -0.62
     intric
    -0.59
     fict
    -0.57
     parted
    -0.56
     undermin
    -0.55
     steroids
    -0.55
     marqu
    -0.55
     propri
    -0.54
     alleg
    -0.54
    POSITIVE LOGITS
     Median
    0.95
     median
    0.88
     GDP
    0.84
    adjusted
    0.77
     total
    0.75
     avg
    0.74
     Percentage
    0.73
    %)
    0.72
     Revenue
    0.71
     Population
    0.71
    Activations Density 0.975%

    No Known Activations