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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15881
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to law and court proceedings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of judicial nominations and appointments

    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
    perture
    -0.75
    ushima
    -0.73
    ombies
    -0.73
    rf
    -0.72
    ivation
    -0.71
    addon
    -0.71
    PF
    -0.71
    gans
    -0.70
    addons
    -0.70
    multipl
    -0.69
    POSITIVE LOGITS
    Judge
    2.30
     Judges
    2.27
     judges
    2.23
     courtroom
    2.21
     Judge
    2.20
     judicial
    2.09
     judge
    2.02
     courthouse
    1.98
     courts
    1.96
     Courts
    1.96
    Activations Density 0.686%

    No Known Activations