© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14319
    Prev
    Next
    INDEX
    Explanations

    the ending punctuation of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the presence of special characters or unusual formatting within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favour
    -1.00
     favor
    -0.99
     metic
    -0.91
     spir
    -0.88
     occas
    -0.83
     targeted
    -0.81
     territorial
    -0.80
     oun
    -0.79
     scram
    -0.79
     reflex
    -0.78
    POSITIVE LOGITS
    But
    1.60
    And
    1.53
    Because
    1.53
    Therefore
    1.53
    They
    1.53
    However
    1.50
    Secondly
    1.47
    He
    1.46
    Yet
    1.46
    It
    1.43
    Activations Density 0.114%

    No Known Activations