© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 15797
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    instances of people being arrested or charged with crimes

    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
    yip
    -0.83
    rings
    -0.80
    ãĥĥãĤ¯
    -0.79
    âĶĢâĶĢâĶĢâĶĢ
    -0.76
     =================================
    -0.74
    paren
    -0.73
    maxwell
    -0.72
    agger
    -0.72
    Especially
    -0.71
    unique
    -0.71
    POSITIVE LOGITS
     underwent
    1.10
     sentenced
    1.10
     ordered
    1.08
     booked
    1.08
     apologized
    1.08
     fined
    1.07
     placed
    1.06
     hauled
    1.03
     issued
    1.02
     reopened
    1.02
    Activations Density 0.215%

    No Known Activations