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

    Neuronpedia

    APICircuit 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. 16685
    Prev
    Next
    INDEX
    Explanations

    mentions of Shiite and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the Shiite religious group and related terms

    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
    oration
    -0.85
    ptroller
    -0.79
    osal
    -0.79
    Merit
    -0.77
    onent
    -0.76
    insula
    -0.74
    orative
    -0.74
    ãģĨ
    -0.74
    ĸļ
    -0.74
    ÑĮ
    -0.74
    POSITIVE LOGITS
     militias
    1.02
     Shia
    0.79
    majority
    0.78
     militia
    0.73
     volunt
    0.73
     dissidents
    0.71
     pilgrims
    0.71
    merga
    0.69
     challeng
    0.68
    istani
    0.67
    Activations Density 0.007%

    No Known Activations