© 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. 11566
    Prev
    Next
    INDEX
    Explanations

    specific patterns or codes within the text

    oai_token-act-pair · gpt-3.5-turbo

    empty lines or breaks in 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
     eleph
    -1.13
    ò
    -1.06
    aditional
    -1.00
    ThumbnailImage
    -0.99
     exting
    -0.98
     pione
    -0.97
     citiz
    -0.97
    senal
    -0.96
    Þ
    -0.95
     tremend
    -0.95
    POSITIVE LOGITS
    ↵
    0.88
    \":
    0.78
    NULL
    0.71
    rou
    0.66
    prem
    0.65
    035
    0.64
    046
    0.63
    Chel
    0.62
    idable
    0.62
    amp
    0.61
    Activations Density 1.005%

    No Known Activations