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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 2132
    Prev
    Next
    INDEX
    Explanations

    legal terms, court-related actions, and judicial decisions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peak
    -0.86
     Forums
    -0.70
    orge
    -0.69
    stats
    -0.65
    ombies
    -0.64
    vell
    -0.64
     ming
    -0.64
     toile
    -0.62
     fielded
    -0.62
     outputs
    -0.62
    POSITIVE LOGITS
     injunction
    1.11
     plaintiffs
    1.05
     unconstitutional
    1.04
     convictions
    1.02
     patent
    1.01
    orney
    0.99
     patents
    0.96
     conviction
    0.94
     suing
    0.90
     lawsuit
    0.90
    Activations Density 0.341%

    No Known Activations