© 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. 2-RES-JB
    11. 19763
    Prev
    Next
    INDEX
    Explanations

    words related to government subsidies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "subsidies" and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ////////////////////////////////
    -0.75
     Fool
    -0.72
    éĽ
    -0.71
    Fax
    -0.70
     Director
    -0.70
    Reloaded
    -0.69
     Governors
    -0.68
     Triangle
    -0.66
    WARE
    -0.65
     Rockefeller
    -0.65
    POSITIVE LOGITS
    chool
    1.04
    oké
    1.04
    iery
    1.04
    sembly
    1.00
     subs
    0.97
    isting
    0.93
    imet
    0.91
    irez
    0.91
    umption
    0.90
    itute
    0.90
    Activations Density 0.005%

    No Known Activations