© 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. 4-RES-JB
    11. 7099
    Prev
    Next
    INDEX
    Explanations

    mentions of friends, family, allies, and supporters

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize relationships with friends and family

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

    No Comments

    Negative Logits
     gears
    -0.71
    oliberal
    -0.68
    ERO
    -0.66
    ument
    -0.66
    ulo
    -0.64
    Phase
    -0.64
     pollut
    -0.63
    Ball
    -0.63
    ãĥ´ãĤ¡
    -0.63
     Pwr
    -0.62
    POSITIVE LOGITS
     neighbours
    0.87
     neighbors
    0.85
     coworkers
    0.84
     strangers
    0.84
     comrades
    0.81
     acquaintances
    0.80
     relatives
    0.78
     whom
    0.77
     classmates
    0.76
     fellow
    0.76
    Activations Density 0.310%

    No Known Activations