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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 13545
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to civil rights and constitutional law

    oai_token-act-pair · gpt-3.5-turbo

    references to constitutional law and legal principles

    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
     Bild
    -0.76
    hap
    -0.73
    aran
    -0.71
    BuyableInstoreAndOnline
    -0.71
     Fukushima
    -0.70
    kos
    -0.70
    arbon
    -0.70
    cheat
    -0.68
    hots
    -0.68
    ourn
    -0.68
    POSITIVE LOGITS
     protections
    0.98
    Attorney
    0.95
     attorneys
    0.95
     appellate
    0.95
     doctrine
    0.92
     justices
    0.91
     unconstitutional
    0.89
     ACLU
    0.89
     statute
    0.89
     jur
    0.88
    Activations Density 0.242%

    No Known Activations