© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4846
    Prev
    Next
    INDEX
    Explanations

    mentions of interactions or relationships with teammates

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "teammate" and words related to teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     addresses
    -0.78
    rollers
    -0.72
     foundations
    -0.70
     governors
    -0.68
     Governors
    -0.66
    tons
    -0.66
     instruments
    -0.66
    blogspot
    -0.66
    ards
    -0.65
     skeletons
    -0.65
    POSITIVE LOGITS
     teammate
    3.73
     classmate
    2.20
     colleague
    1.83
     comrade
    1.56
     teammates
    1.51
     buddy
    1.41
     cowork
    1.38
     linem
    1.38
     roommate
    1.36
     collaborator
    1.34
    Activations Density 0.018%

    No Known Activations