© 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. 10-RES-JB
    11. 16158
    Prev
    Next
    INDEX
    Explanations

    web links, particularly those directing to further information or comments on a topic

    oai_token-act-pair · gpt-3.5-turbo

    symbols and special characters commonly used in URLs or hyperlinks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pavilion
    -0.72
     Mayo
    -0.64
     Marse
    -0.63
     Soldiers
    -0.62
     Typhoon
    -0.61
     Carbuncle
    -0.61
     Farming
    -0.60
     Franch
    -0.60
     Bloody
    -0.60
     Enlight
    -0.59
    POSITIVE LOGITS
    º
    1.45
    ¡
    1.33
    ½
    1.32
    ´
    1.32
    į
    1.31
    ¿
    1.31
    »
    1.31
    Ń
    1.30
    £
    1.30
    ²
    1.29
    Activations Density 0.090%

    No Known Activations