© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6163
    Prev
    Next
    INDEX
    Explanations

    random characters, potentially indicating a coding-related purpose

    oai_token-act-pair · gpt-3.5-turbo

    patterns of Cyrillic script characters

    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
     reconc
    -0.74
    urion
    -0.68
     custody
    -0.67
    axter
    -0.63
     licensing
    -0.63
    irtual
    -0.62
     overlap
    -0.61
    ected
    -0.61
    nown
    -0.61
    drawn
    -0.61
    POSITIVE LOGITS
     Ð
    1.11
     ÙĪ
    1.11
    н
    1.08
    Ø©
    1.05
    ÏĤ
    1.02
    1.02
    Ñı
    0.99
    и
    0.96
    ÙĨ
    0.94
    е
    0.93
    Activations Density 0.065%

    No Known Activations