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. 398
    Prev
    Next
    INDEX
    Explanations

    references to historical documents, particularly the Declaration of Independence

    oai_token-act-pair · gpt-3.5-turbo

    references to the Declaration of Independence and related legal documents

    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
    alez
    -0.70
    skin
    -0.68
    asu
    -0.68
    icago
    -0.64
    ROR
    -0.63
    OTOS
    -0.60
    iday
    -0.59
    elve
    -0.57
     Insider
    -0.56
    wig
    -0.56
    POSITIVE LOGITS
     declaration
    0.93
    aration
    0.91
     declares
    0.85
     declarations
    0.84
     declaring
    0.83
    gements
    0.79
    arations
    0.77
    Decl
    0.77
     declare
    0.76
     proclaiming
    0.74
    Activations Density 0.023%

    No Known Activations