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. 11-RES-JB
    6. 4307
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    recurring definite articles and words related to government or legal terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    morrow
    -0.75
    cape
    -0.74
    thood
    -0.74
    stellar
    -0.73
    ,...
    -0.71
    orge
    -0.70
    ipeg
    -0.70
    iour
    -0.70
    ibo
    -0.69
    Ò
    -0.69
    POSITIVE LOGITS
     plaintiffs
    1.42
     Constitution
    1.36
     Court
    1.32
     statute
    1.32
     justices
    1.28
     constitution
    1.23
     plaintiff
    1.23
     Supreme
    1.19
     legality
    1.14
     doctrine
    1.13
    Activations Density 0.266%

    No Known Activations