© 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. 2-RES-JB
    11. 8948
    Prev
    Next
    INDEX
    Explanations

    phrases relating to former Federal Reserve Chair Ben Bernanke

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant economic figures, particularly Ben Bernanke and Janet Yellen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kali
    -0.75
    ORED
    -0.71
     Trop
    -0.70
     Nort
    -0.70
     Cot
    -0.67
    Mich
    -0.66
    Tam
    -0.66
     Antar
    -0.66
    HP
    -0.65
     Slov
    -0.64
    POSITIVE LOGITS
    anke
    1.61
    hyde
    1.01
    psey
    0.98
    jriwal
    0.96
    steen
    0.94
    ellen
    0.92
    iller
    0.91
    iets
    0.89
    iture
    0.85
    icer
    0.81
    Activations Density 0.015%

    No Known Activations