© 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. 6-RES-JB
    11. 11657
    Prev
    Next
    INDEX
    Explanations

    legal terms and courtroom-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    legal terms and phrases associated with court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colored
    -0.76
     favors
    -0.74
     someday
    -0.73
    defense
    -0.73
    Defense
    -0.72
    Arizona
    -0.72
    Texas
    -0.72
    bors
    -0.71
     Hawai
    -0.70
    Utah
    -0.70
    POSITIVE LOGITS
     realise
    1.22
     recognise
    1.22
     £
    1.19
     apologise
    1.16
     centre
    1.15
     apologised
    1.15
     recognised
    1.13
     organisers
    1.11
     analyse
    1.11
     aluminium
    1.10
    Activations Density 3.314%

    No Known Activations