© 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. 2-RES-JB
    11. 20975
    Prev
    Next
    INDEX
    Explanations

    financial and data-centric terms like "analysis," "budget," and "tax cuts."

    oai_token-act-pair · gpt-3.5-turbo

    analytical terms and phrases related to reporting or commentary

    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
    ances
    -0.87
    raz
    -0.75
    ages
    -0.73
    rolog
    -0.68
    seller
    -0.68
    aged
    -0.66
    rolled
    -0.62
    ulum
    -0.62
    emaker
    -0.61
    eded
    -0.61
    POSITIVE LOGITS
    Analysis
    1.29
     Interpret
    0.80
    livious
    0.76
    uador
    0.75
     Weak
    0.73
    notations
    0.70
     Insight
    0.70
     Analysis
    0.70
     Scan
    0.70
    imbabwe
    0.69
    Activations Density 0.013%

    No Known Activations