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. 15358
    Prev
    Next
    INDEX
    Explanations

    instances of legal action, specifically lawsuits

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sue" and its variations

    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
    atomic
    -0.78
    obyl
    -0.78
    acho
    -0.74
    lot
    -0.74
    existent
    -0.72
    adden
    -0.70
    translation
    -0.70
    adequ
    -0.69
    nown
    -0.69
    apo
    -0.69
    POSITIVE LOGITS
     suing
    0.92
     against
    0.88
     sue
    0.86
     sued
    0.84
     him
    0.71
     Hansen
    0.69
     Gloria
    0.69
     anonymously
    0.68
     AGA
    0.66
     Judd
    0.66
    Activations Density 0.027%

    No Known Activations