© 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. 7-RES-JB
    11. 19201
    Prev
    Next
    INDEX
    Explanations

    titles or mentions of positions, specifically related to "Chief of Staff."

    oai_token-act-pair · gpt-3.5-turbo

    references to "chief of staff" or related positions in an organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sensor
    -0.70
    ETA
    -0.68
     cruelty
    -0.68
     dab
    -0.66
    200000
    -0.65
    abouts
    -0.65
    gro
    -0.62
    past
    -0.60
    ãĥŃ
    -0.59
    theless
    -0.59
    POSITIVE LOGITS
    chairs
    0.76
    heed
    0.75
    achev
    0.74
    yrim
    0.71
    chair
    0.70
    oice
    0.69
     secretaries
    0.69
    andowski
    0.69
     Personnel
    0.69
     Advisor
    0.69
    Activations Density 0.015%

    No Known Activations