© 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. 11-RES-JB
    11. 21609
    Prev
    Next
    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and quotes

    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
     buoy
    -0.84
     caveat
    -0.83
     fallacy
    -0.82
     outline
    -0.79
     report
    -0.79
     attribute
    -0.78
     veil
    -0.78
     premise
    -0.78
     draw
    -0.77
     drawback
    -0.77
    POSITIVE LOGITS
    their
    1.96
    the
    1.85
    his
    1.84
    them
    1.82
    another
    1.77
    our
    1.74
    your
    1.73
    those
    1.70
    someone
    1.63
    every
    1.63
    Activations Density 0.222%

    No Known Activations