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. 19749
    Prev
    Next
    INDEX
    Explanations

    legal terms and descriptions of legal actions such as lawsuits and court proceedings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of lawsuits and legal actions

    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
    odiac
    -0.67
    oding
    -0.66
    chel
    -0.66
    ritical
    -0.65
     warmth
    -0.64
    RIP
    -0.64
    vell
    -0.63
    zsche
    -0.63
     Personality
    -0.62
     Britann
    -0.61
    POSITIVE LOGITS
     sued
    1.75
     suing
    1.61
     plaintiffs
    1.51
     alleges
    1.49
     filed
    1.47
     petition
    1.46
     contends
    1.42
     sue
    1.39
     allege
    1.37
     contended
    1.37
    Activations Density 0.690%

    No Known Activations