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. 5221
    Prev
    Next
    INDEX
    Explanations

    language related to legal matters and agreements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating legal agreements or settlements

    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
     Vaugh
    -0.89
    jri
    -0.75
     Seym
    -0.73
    ulla
    -0.71
    akespe
    -0.70
    enegger
    -0.70
     convol
    -0.69
     Jagu
    -0.69
    swick
    -0.68
    farious
    -0.68
    POSITIVE LOGITS
     largeDownload
    0.58
     Abandon
    0.57
     Released
    0.55
     CentOS
    0.50
     AMD
    0.49
     nutshell
    0.49
     Rey
    0.49
     Windows
    0.49
     Squirrel
    0.48
     GHC
    0.48
    Activations Density 0.666%

    No Known Activations