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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5479
    Prev
    Next
    INDEX
    Explanations

    references to different ethnic groups or communities

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people and their identities

    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
    inventoryQuantity
    -0.88
    Effective
    -0.83
    Delivery
    -0.80
    FIN
    -0.77
    Accessory
    -0.77
    clips
    -0.74
    LV
    -0.74
    ctor
    -0.71
    vous
    -0.69
    ICE
    -0.67
    POSITIVE LOGITS
     peoples
    1.10
     civilizations
    0.90
     nations
    0.86
     inhab
    0.86
    oples
    0.85
    hell
    0.81
     enslaved
    0.80
     cultures
    0.79
    agos
    0.79
     tribes
    0.78
    Activations Density 0.050%

    No Known Activations