© 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. 1-RES-JB
    11. 11520
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and people involved in those cases

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of individuals involved in a high-profile legal case

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -0.76
    ãĥł
    -0.75
    href
    -0.75
    sector
    -0.75
    Asia
    -0.74
    itions
    -0.70
    utm
    -0.69
    é£
    -0.68
    favorite
    -0.68
    ition
    -0.66
    POSITIVE LOGITS
     Zimmerman
    1.21
     Trayvon
    0.78
     cones
    0.74
    ufact
    0.72
    enegger
    0.71
     MLG
    0.70
     Bundy
    0.70
     sleeves
    0.69
     helic
    0.67
     Gott
    0.67
    Activations Density 0.010%

    No Known Activations