© 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. 10-RES-JB
    11. 7802
    Prev
    Next
    INDEX
    Explanations

    photographs and images of individuals, such as politicians, royalty, and celebrities

    oai_token-act-pair · gpt-3.5-turbo

    references to photographs or images related to individuals and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imester
    -0.74
    cipled
    -0.72
    issan
    -0.69
    izons
    -0.69
    ItemTracker
    -0.68
    politics
    -0.67
    ainer
    -0.67
    ente
    -0.65
    Berry
    -0.64
    Parameter
    -0.64
    POSITIVE LOGITS
     smiling
    1.15
     grinning
    1.07
     kneeling
    1.02
     adorned
    0.99
     interacting
    0.99
     behaving
    0.94
     surrounded
    0.94
     undergoing
    0.93
     hugging
    0.91
     enjoying
    0.91
    Activations Density 0.490%

    No Known Activations