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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11673
    Prev
    Next
    INDEX
    Explanations

    references to historical figures or specific names, especially related to Jefferson

    oai_token-act-pair · gpt-3.5-turbo

    references to Thomas Jefferson

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.83
    lator
    -0.74
    uling
    -0.70
    other
    -0.68
    comed
    -0.66
    arer
    -0.66
    eq
    -0.66
    atics
    -0.65
    spring
    -0.65
    fare
    -0.65
    POSITIVE LOGITS
     Jefferson
    1.12
     Parish
    1.06
     Davis
    0.91
    sburg
    0.89
    agne
    0.85
    shire
    0.80
     Adams
    0.79
     County
    0.78
     Mills
    0.78
    izabeth
    0.74
    Activations Density 0.018%

    No Known Activations