© 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. 3434
    Prev
    Next
    INDEX
    Explanations

    names or terms with a particular pattern, where a capital letter is followed by a lowercase 'y' or 'o'

    oai_token-act-pair · gpt-3.5-turbo

    vowel-heavy words or names

    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
    enegger
    -0.83
    Reviewer
    -0.74
    irlf
    -0.74
    iaries
    -0.70
     Flavoring
    -0.64
    */(
    -0.62
    =-=-=-=-
    -0.62
    >>\
    -0.62
     certs
    -0.62
    merce
    -0.61
    POSITIVE LOGITS
     Richards
    0.73
     Staples
    0.72
    HUD
    0.71
    Ľ
    0.71
     Guerrero
    0.71
    Dispatch
    0.70
     Rich
    0.69
    elman
    0.69
    oidal
    0.69
     Morales
    0.66
    Activations Density 0.087%

    No Known Activations