© 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. 10428
    Prev
    Next
    INDEX
    Explanations

    characters from a specific language (like Cyrillic) and possibly numbers or symbols

    oai_token-act-pair · gpt-3.5-turbo

    non-standard or special characters and symbols in the text

    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
     Gutenberg
    -0.95
    eur
    -0.77
    inelli
    -0.75
    eering
    -0.74
     CLSID
    -0.74
     tee
    -0.73
    raints
    -0.70
    uncture
    -0.70
    enegger
    -0.68
     Syndicate
    -0.66
    POSITIVE LOGITS
    atar
    0.91
    cle
    0.79
    comed
    0.77
    adesh
    0.77
    å¸
    0.76
    ipop
    0.73
    uthor
    0.72
    usra
    0.72
    ±
    0.72
    âĺĨ
    0.71
    Activations Density 0.011%

    No Known Activations