© 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. 11232
    Prev
    Next
    INDEX
    Explanations

    the word "but" followed by a description or contrast

    oai_token-act-pair · gpt-3.5-turbo

    instances of contrast or exception

    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
    lement
    -0.73
    ealing
    -0.66
    ammed
    -0.65
    esc
    -0.65
    ISH
    -0.63
    à¥
    -0.63
    aez
    -0.63
    legate
    -0.62
    adr
    -0.62
    IZ
    -0.62
    POSITIVE LOGITS
     none
    1.35
     nothing
    1.14
     mostly
    1.10
     generally
    1.01
     invariably
    1.00
     ultimately
    1.00
     alas
    1.00
     nowhere
    0.99
     overall
    0.99
     chiefly
    0.97
    Activations Density 0.239%

    No Known Activations