© 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. 18502
    Prev
    Next
    INDEX
    Explanations

    references to obtaining more information or details on a topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a request for additional information

    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
    NetMessage
    -0.87
    hered
    -0.73
    ibles
    -0.73
    hare
    -0.73
    FontSize
    -0.73
    aired
    -0.72
    ress
    -0.72
    pex
    -0.71
    wark
    -0.71
    imaru
    -0.70
    POSITIVE LOGITS
     information
    1.39
     info
    1.36
     details
    1.23
     insight
    1.12
     insights
    1.03
     detailed
    1.02
     detail
    1.00
     INFORMATION
    0.95
     updates
    0.93
     Information
    0.92
    Activations Density 0.039%

    No Known Activations