Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 16527
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Shi"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific ethnic or cultural groups, particularly related to the Shiite Muslim community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fulness
    -0.76
    code
    -0.73
    codes
    -0.70
    thel
    -0.69
    mint
    -0.66
    fish
    -0.65
    fully
    -0.65
    transform
    -0.64
    quest
    -0.64
     Vigil
    -0.64
    POSITIVE LOGITS
    andum
    1.04
    arians
    0.94
    ¯¯¯¯
    0.92
    terness
    0.85
    kee
    0.84
    arian
    0.80
     Hou
    0.78
    agin
    0.78
    aries
    0.77
    atives
    0.76
    Activations Density 0.014%

    No Known Activations