© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6129
    Prev
    Next
    INDEX
    Explanations

    instances of the word "court"

    oai_token-act-pair · gpt-3.5-turbo

    references to court-related concepts and legal proceedings

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

    No Comments

    Negative Logits
     livest
    -0.79
    ï¸ı
    -0.70
     Pyro
    -0.70
    jiang
    -0.68
    irst
    -0.68
     Marketable
    -0.67
     plent
    -0.67
     Remain
    -0.65
    ku
    -0.64
     Dawn
    -0.64
    POSITIVE LOGITS
    rooms
    1.07
    esan
    1.03
    room
    0.95
     hearings
    0.87
    Court
    0.82
     judge
    0.80
     court
    0.80
     proceedings
    0.79
     rulings
    0.78
    auld
    0.78
    Activations Density 0.031%

    No Known Activations