© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 8523
    Prev
    Next
    INDEX
    Explanations

    mentions of or related to individuals in positions of authority or leadership, particularly with the title "Chief."

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the title "Chief."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ajor
    -0.89
    phis
    -0.80
    schild
    -0.79
     destro
    -0.79
    pez
    -0.79
    staking
    -0.78
    ngth
    -0.77
    \/\/
    -0.77
    vous
    -0.73
    debian
    -0.73
    POSITIVE LOGITS
     Chief
    0.87
     Executive
    0.86
    doms
    0.85
     Petty
    0.83
     Scientist
    0.81
    Chief
    0.79
    iary
    0.79
     Engineer
    0.77
     Warrant
    0.75
     Operating
    0.74
    Activations Density 0.013%

    No Known Activations