© 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. 4-RES-JB
    11. 10385
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "economics."

    oai_token-act-pair · gpt-3.5-turbo

    references to economics

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

    No Comments

    Negative Logits
    ometown
    -0.81
    fires
    -0.79
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.75
    ivas
    -0.75
    lain
    -0.72
    Pont
    -0.71
    ¯¯
    -0.71
    ittees
    -0.70
    arters
    -0.70
    ificant
    -0.69
    POSITIVE LOGITS
     textbooks
    0.96
     economics
    0.93
     profession
    0.87
     equations
    0.85
     professor
    0.80
    gebra
    0.80
     textbook
    0.76
     economist
    0.76
     resil
    0.75
     bureau
    0.75
    Activations Density 0.012%

    No Known Activations