© 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. 9-RES-JB
    11. 11217
    Prev
    Next
    INDEX
    Explanations

    different forms of the phrase "There's a."

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the character "âĢ", which likely represents a typographical error or formatting issue in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Palest
    -0.70
    Buyable
    -0.65
     Gan
    -0.64
     Opera
    -0.64
     Manhattan
    -0.62
     Tanz
    -0.61
     Paras
    -0.61
     Jinn
    -0.61
     Amit
    -0.60
     Narc
    -0.59
    POSITIVE LOGITS
    ı
    1.04
    ¬
    1.03
    £
    1.01
    į
    1.00
    Ń
    0.99
    º
    0.97
    ¡
    0.97
    ĭ
    0.95
    ¼
    0.95
    Ĵ
    0.94
    Activations Density 0.029%

    No Known Activations