© 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. 6-RES-JB
    11. 12850
    Prev
    Next
    INDEX
    Explanations

    references to physical actions involving handcuffs and physical descriptions of people in restraining situations

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement and restraint

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.90
    Rate
    -0.80
    otten
    -0.77
    ãĤ¼
    -0.76
    ML
    -0.73
    development
    -0.71
    ovie
    -0.70
    Course
    -0.70
     VIDEOS
    -0.69
    Feed
    -0.69
    POSITIVE LOGITS
     sleeves
    1.29
     robes
    1.23
     adorned
    1.16
     sleeve
    1.15
     draped
    1.10
     clasp
    1.10
     straps
    1.09
     cloth
    1.06
     handcuffed
    1.06
     clad
    1.05
    Activations Density 0.631%

    No Known Activations