© 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. 4191
    Prev
    Next
    INDEX
    Explanations

    words related to different industries and sectors, such as wine industry, electric grid, housing landscape, beer industry, banking sector, and education spending

    oai_token-act-pair · gpt-3.5-turbo

    references to economic sectors and industries

    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
    arget
    -0.65
    vous
    -0.63
     Gain
    -0.62
    ather
    -0.60
     Cove
    -0.60
    itious
    -0.60
    erous
    -0.59
    dding
    -0.59
    endez
    -0.59
    arious
    -0.57
    POSITIVE LOGITS
     revolves
    0.86
     relies
    0.82
     differs
    0.80
     landscape
    0.78
     consists
    0.77
     empire
    0.76
     spans
    0.75
     evolves
    0.74
    needs
    0.73
     contains
    0.72
    Activations Density 0.489%

    No Known Activations