Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 4473
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters, specifically divorce

    oai_token-act-pair · gpt-3.5-turbo

    mentions of divorce and related legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.88
    ibaba
    -0.71
    eyes
    -0.67
    culosis
    -0.66
    sung
    -0.66
    oken
    -0.65
     McMaster
    -0.65
    velength
    -0.65
    ambers
    -0.65
    iday
    -0.64
    POSITIVE LOGITS
    orce
    0.86
     proceedings
    0.83
    creen
    0.82
     divor
    0.81
     divorce
    0.80
     decree
    0.73
    aration
    0.73
     Resolution
    0.72
    rupt
    0.71
     settlement
    0.71
    Activations Density 0.041%

    No Known Activations