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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    6. 6074
    Prev
    Next
    INDEX
    Explanations

    legal or jurisdictional terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to legal jurisdictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orns
    -0.78
    itches
    -0.72
    esta
    -0.71
    erm
    -0.70
    tk
    -0.70
    tons
    -0.69
    iked
    -0.67
    ulton
    -0.66
    irl
    -0.66
    ighter
    -0.65
    POSITIVE LOGITS
     jurisdiction
    1.06
    ignty
    0.80
    alties
    0.80
    abl
    0.79
    isd
    0.78
     authority
    0.75
     delegated
    0.74
     jurisdictions
    0.74
     jerk
    0.68
     sanction
    0.68
    Activations Density 0.016%

    No Known Activations