Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 19201
    Prev
    Next
    INDEX
    Explanations

    titles or references to people in positions of authority, specifically those with the title "Chief"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of police chiefs

    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
    pez
    -0.85
    schild
    -0.80
    ICAN
    -0.80
    ppo
    -0.79
    etimes
    -0.79
    aver
    -0.78
    adr
    -0.78
    AAF
    -0.76
    ted
    -0.76
    ugi
    -0.76
    POSITIVE LOGITS
     Chief
    1.11
    Chief
    1.04
     Engineer
    0.83
     Scientist
    0.79
     Executive
    0.78
     chief
    0.77
     Marshal
    0.76
     Editor
    0.75
     Headquarters
    0.73
     Officer
    0.73
    Activations Density 0.010%

    No Known Activations