© 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. 11-RES-JB
    6. 23002
    Prev
    Next
    INDEX
    Explanations

    pronouns and gender-specific nouns referring to a person

    oai_token-act-pair · gpt-3.5-turbo

    pronouns referring to people, particularly focusing on "he" and "she."

    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
     concluding
    -0.77
    Effective
    -0.76
    ĵĺ
    -0.74
    PDATE
    -0.71
    ISION
    -0.70
     contingency
    -0.68
    catentry
    -0.66
     contention
    -0.66
     Additional
    -0.65
     Prel
    -0.64
    POSITIVE LOGITS
     hates
    1.45
     ain
    1.30
     wears
    1.28
     sucks
    1.26
     loves
    1.26
     smells
    1.19
     eats
    1.17
     owns
    1.17
     smokes
    1.15
     sleeps
    1.14
    Activations Density 0.319%

    No Known Activations