© 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. 1-RES-JB
    11. 1982
    Prev
    Next
    INDEX
    Explanations

    prominent figures holding positions of authority

    oai_token-act-pair · gpt-3.5-turbo

    the term "chief" in various contexts related to leadership positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etimes
    -0.80
    avery
    -0.80
    schild
    -0.75
    aving
    -0.74
    grades
    -0.73
    nikov
    -0.73
    adr
    -0.71
    irc
    -0.70
    inters
    -0.70
    encing
    -0.68
    POSITIVE LOGITS
     chief
    1.17
     Chief
    1.02
    chief
    0.99
    Chief
    0.98
     executive
    0.94
     executives
    0.90
     chiefs
    0.83
     exec
    0.78
    doms
    0.76
     strategist
    0.76
    Activations Density 0.017%

    No Known Activations