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. 10-RES-JB
    6. 449
    Prev
    Next
    INDEX
    Explanations

    Proper names, particularly with the last name "Marwan Ashraf"

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals or figures in a contextually significant scenario

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wilmington
    -0.95
     Titanic
    -0.80
     Colossus
    -0.79
     Spokane
    -0.75
     Tacoma
    -0.75
     Pike
    -0.73
     Californ
    -0.73
    Columb
    -0.72
     Poles
    -0.72
     corporations
    -0.71
    POSITIVE LOGITS
    Allah
    1.69
     Hussain
    1.69
    rahim
    1.66
     Mahm
    1.66
    uddin
    1.62
     Rahman
    1.62
     Hasan
    1.61
     Ahmed
    1.61
     Ahmad
    1.61
     Sheikh
    1.59
    Activations Density 0.410%

    No Known Activations