© 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. 2-RES-JB
    11. 390
    Prev
    Next
    INDEX
    Explanations

    the word 'colleague'

    oai_token-act-pair · gpt-4-turbo

    mentions of colleagues or coworkers

    oai_token-act-pair · gpt-3.5-turbo

    references to colleagues or teammates

    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
    itters
    -0.93
    avers
    -0.86
    ingers
    -0.85
    etting
    -0.84
    liga
    -0.83
    uits
    -0.80
    cale
    -0.80
    olia
    -0.79
    ourcing
    -0.78
    aida
    -0.78
    POSITIVE LOGITS
     colleague
    0.95
     classmate
    0.84
     Ally
    0.83
    nered
    0.81
     comrade
    0.78
     laureate
    0.78
    lier
    0.74
     Laure
    0.73
     Prosper
    0.71
     cowork
    0.71
    Activations Density 0.032%

    No Known Activations