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. 10-RES-JB
    6. 3897
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to judicial system and courts

    oai_token-act-pair · gpt-3.5-turbo

    references to judicial systems and legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rolet
    -0.80
     Soldier
    -0.78
    ulus
    -0.74
     Osc
    -0.70
     Rivals
    -0.68
    retched
    -0.66
    ontent
    -0.66
     Kund
    -0.65
     Brands
    -0.65
    lund
    -0.64
    POSITIVE LOGITS
     rulings
    1.28
    rooms
    1.02
     justices
    1.01
     appellate
    1.01
     adjud
    1.00
     proceedings
    0.99
    hip
    0.97
     ruling
    0.97
     Gorsuch
    0.97
     clerks
    0.97
    Activations Density 0.083%

    No Known Activations