© 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. 2633
    Prev
    Next
    INDEX
    Explanations

    references to coworkers or associates

    oai_token-act-pair · gpt-3.5-turbo

    references to colleagues in a professional context

    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
    ruction
    -0.72
     sale
    -0.66
     manufacture
    -0.60
    vable
    -0.59
    :(
    -0.59
     WITHOUT
    -0.57
     selling
    -0.56
     Abyssal
    -0.56
     \"
    -0.55
    trap
    -0.55
    POSITIVE LOGITS
     colleagues
    3.74
     colleague
    2.70
     coworkers
    2.63
     collaborators
    2.15
     peers
    2.03
     classmates
    1.92
     comrades
    1.90
     teammates
    1.83
     contemporaries
    1.82
     superiors
    1.81
    Activations Density 0.013%

    No Known Activations