© 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. 10-RES-JB
    11. 2868
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating possession

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships and personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.87
    ibaba
    -0.85
    utra
    -0.76
    ignty
    -0.72
    trop
    -0.71
    lihood
    -0.70
    IUM
    -0.70
    daq
    -0.70
    ciation
    -0.69
    ruction
    -0.69
    POSITIVE LOGITS
     superiors
    1.58
     wife
    1.55
     girlfriend
    1.52
     friend
    1.52
     friends
    1.51
     fellow
    1.48
     fian
    1.47
     buddies
    1.47
     cousin
    1.46
     colleague
    1.46
    Activations Density 0.184%

    No Known Activations