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. 18464
    Prev
    Next
    INDEX
    Explanations

    names of judges

    oai_token-act-pair · gpt-3.5-turbo

    references to judges and their rulings in legal contexts

    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
     IMAGES
    -0.84
    natureconservancy
    -0.83
    perture
    -0.75
    teness
    -0.71
     Paste
    -0.69
    photos
    -0.67
     srfAttach
    -0.66
    reenshots
    -0.65
     weap
    -0.65
     grassroots
    -0.64
    POSITIVE LOGITS
     rulings
    1.31
     ruling
    1.26
     ruled
    1.21
    Judge
    1.19
     verdict
    1.17
     sided
    1.16
     upheld
    1.13
     judge
    1.11
     upholding
    1.10
     overturned
    1.09
    Activations Density 0.256%

    No Known Activations