© 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 EvalsExportsinterp-engineNEWAPI 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. 9568
    Prev
    Next
    INDEX
    Explanations

    mentions of staff members in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to staff members or personnel

    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
     Prosper
    -0.79
    mobi
    -0.72
     Fem
    -0.71
    200000
    -0.67
     Pac
    -0.67
     Geological
    -0.63
     Roosevelt
    -0.62
    asta
    -0.61
    ICO
    -0.61
     Geo
    -0.61
    POSITIVE LOGITS
     staff
    1.12
    andowski
    0.96
    staff
    0.96
    irtual
    0.91
     personnel
    0.89
     staffers
    0.87
     interns
    0.87
    anooga
    0.81
     members
    0.81
    iannopoulos
    0.81
    Activations Density 0.024%

    No Known Activations