© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 3010
    Prev
    Next
    INDEX
    Explanations

    mentions of specific words or phrases related to Sikh culture or people

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to individuals with the name 'Sik', and to a lesser extent, variations or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ãĤ¨ãĥ«
    -0.69
    sis
    -0.57
     moons
    -0.56
    é¾įåĸļ士
    -0.56
    aded
    -0.56
    ãģ®é
    -0.56
     Grizz
    -0.55
     capitals
    -0.54
    sin
    -0.54
    ographies
    -0.53
    POSITIVE LOGITS
    į
    1.02
    ĭ
    0.94
    eca
    0.93
    antam
    0.80
    ulously
    0.80
    ables
    0.79
    able
    0.78
    ĩ
    0.78
    eering
    0.77
    Ī
    0.76
    Activations Density 0.092%

    No Known Activations