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. 3-RES-JB
    6. 14695
    Prev
    Next
    INDEX
    Explanations

    references to legal authorities and legal proceedings, such as magistrates and judges

    oai_token-act-pair · gpt-3.5-turbo

    mentions of magistrates and related titles or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORE
    -0.81
    shaw
    -0.75
    arenthood
    -0.68
    Æ
    -0.68
    PER
    -0.68
    bie
    -0.66
    ted
    -0.65
    tons
    -0.64
    bies
    -0.64
    ggies
    -0.64
    POSITIVE LOGITS
    istrate
    1.50
    istrates
    1.47
     magistrate
    1.23
     judge
    1.03
    merce
    0.96
     court
    0.91
     Court
    0.87
     oun
    0.85
     fined
    0.84
     Judge
    0.81
    Activations Density 0.011%

    No Known Activations