© 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. 1-RES-JB
    11. 3610
    Prev
    Next
    INDEX
    Explanations

    mentions of the phrase "New Deal", referring to a specific economic policy and set of reforms implemented in the United States in the 1930s

    oai_token-act-pair · gpt-3.5-turbo

    references to the New Deal and related policies or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indigenous
    -0.69
    untu
    -0.69
    76561
    -0.67
    RAFT
    -0.66
    gotten
    -0.64
    İĭ
    -0.64
    andr
    -0.62
    ß
    -0.61
    thodox
    -0.60
     Ancients
    -0.60
    POSITIVE LOGITS
    deal
    1.47
    Deal
    1.45
    ership
    1.27
     Deal
    1.25
     Deals
    0.93
     Dealer
    0.90
    builder
    0.85
     horizont
    0.85
    lear
    0.83
    buster
    0.81
    Activations Density 0.011%

    No Known Activations