© 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. 11-RES-JB
    11. 14819
    Prev
    Next
    INDEX
    Explanations

    mentions or instances of the word "one" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to obtaining or acquiring something

    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
    osponsors
    -0.79
    grounds
    -0.77
    uts
    -0.73
    lations
    -0.72
    children
    -0.72
    shed
    -0.71
    hers
    -0.66
    sav
    -0.62
     Vaugh
    -0.62
     distances
    -0.62
    POSITIVE LOGITS
     of
    1.16
     hundred
    1.02
     thing
    0.93
     ounce
    0.93
     thereof
    0.92
     heck
    0.89
     sided
    0.86
     thousand
    0.85
     Hundred
    0.83
    esan
    0.80
    Activations Density 0.095%

    No Known Activations