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. 1-RES-JB
    6. 17957
    Prev
    Next
    INDEX
    Explanations

    terms related to Shiite and Persian cultures or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to the Shiite Muslim group and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estern
    -0.92
    umin
    -0.79
    sers
    -0.78
    shaw
    -0.77
    ÑĮ
    -0.77
    abet
    -0.76
    Merit
    -0.75
    rol
    -0.75
    worthy
    -0.74
    worthiness
    -0.72
    POSITIVE LOGITS
     Shiite
    1.04
     cous
    0.84
    Û
    0.80
    istani
    0.75
     pancakes
    0.74
     militias
    0.74
     shrine
    0.72
     curls
    0.69
     artisan
    0.69
     hunter
    0.68
    Activations Density 0.008%

    No Known Activations