Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21404
    Prev
    Next
    INDEX
    Explanations

    specifically the word "economists" or related variations

    oai_token-act-pair · gpt-3.5-turbo

    references to economists and their discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vas
    -0.70
     Squad
    -0.70
    aint
    -0.62
     Viper
    -0.61
     Trident
    -0.61
     flares
    -0.61
    SPA
    -0.61
     Command
    -0.60
     Grind
    -0.60
    cess
    -0.60
    POSITIVE LOGITS
     economists
    3.55
     economist
    3.13
     Econom
    2.20
     Economics
    2.10
     economics
    2.06
    Econom
    2.02
     Economist
    1.95
     Keynes
    1.70
    Economic
    1.64
     mathemat
    1.60
    Activations Density 0.021%

    No Known Activations