© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10765
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court rulings

    oai_token-act-pair · gpt-3.5-turbo

    references to judicial rulings and legal decisions

    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
    ohyd
    -0.72
    asus
    -0.71
    ople
    -0.69
     weap
    -0.66
    nel
    -0.66
    Plot
    -0.65
     Volunte
    -0.64
    ope
    -0.63
     Volunteers
    -0.63
     behaviours
    -0.63
    POSITIVE LOGITS
     upholding
    1.38
     overturn
    1.24
     legalizing
    1.18
     invalid
    1.07
     upheld
    1.07
     awarding
    0.99
     uphold
    0.99
     dismissing
    0.97
     rejecting
    0.95
     rulings
    0.95
    Activations Density 0.073%

    No Known Activations