© 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. 11-RES-JB
    11. 7689
    Prev
    Next
    INDEX
    Explanations

    personal experiences and relationships

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.76
    vernment
    -0.72
    urden
    -0.70
    ilib
    -0.70
    ellation
    -0.69
    generated
    -0.69
    Ô
    -0.68
    redits
    -0.68
     apiece
    -0.66
    beit
    -0.66
    POSITIVE LOGITS
     girlfriend
    1.41
     roommate
    1.39
     boyfriend
    1.37
     mom
    1.34
     grandma
    1.34
     roomm
    1.34
     dad
    1.33
     niece
    1.33
     fiance
    1.30
     wife
    1.30
    Activations Density 0.231%

    No Known Activations