© 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. 6441
    Prev
    Next
    INDEX
    Explanations

    words related to economic and political events and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to financial statistics and economic recovery

    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
     wearer
    -0.70
     listener
    -0.67
    Chat
    -0.62
    ibli
    -0.62
    contact
    -0.60
    iquette
    -0.60
    antam
    -0.60
     convers
    -0.58
     viewer
    -0.57
    tainment
    -0.57
    POSITIVE LOGITS
    failed
    1.11
     failed
    1.05
     resulted
    1.04
     succeeded
    1.02
     coincided
    0.98
     culminated
    0.96
     undermined
    0.95
     lacked
    0.94
     worsened
    0.94
     ceased
    0.93
    Activations Density 0.851%

    No Known Activations