© 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. 11-RES-JB
    11. 199
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement actions and arrests

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to arrests and individuals involved in criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disasters
    -0.73
     reinvent
    -0.63
    thumbnails
    -0.63
    whel
    -0.63
    inventoryQuantity
    -0.61
     bounce
    -0.61
    Ħ¢
    -0.61
    "))
    -0.60
    regnancy
    -0.60
     renaissance
    -0.59
    POSITIVE LOGITS
     suspected
    1.05
     suspects
    0.92
     suspect
    0.87
     overnight
    0.76
     shortly
    0.76
     after
    0.75
     pending
    0.73
     tresp
    0.72
     accused
    0.69
     indefinitely
    0.69
    Activations Density 0.239%

    No Known Activations