© 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. 11363
    Prev
    Next
    INDEX
    Explanations

    references to the article author, Opie Ortiz

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Op" and its variations, indicating a focus on "Op" as a significant term or concept

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.83
    wagen
    -0.80
    åŃIJ
    -0.74
    ãĥīãĥ©ãĤ´ãĥ³
    -0.71
    ãĥ¯ãĥ³
    -0.70
     wart
    -0.70
    =~=~
    -0.68
    ¶ħ
    -0.68
     mileage
    -0.68
    é¾įå¥ij士
    -0.67
    POSITIVE LOGITS
    aque
    1.26
    osite
    1.26
    inion
    1.13
    aqu
    1.07
    onent
    1.06
    rah
    1.06
    yright
    1.05
    ulent
    1.01
    ression
    0.98
    hel
    0.97
    Activations Density 0.029%

    No Known Activations