Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14522
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to a specific individual

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific male subject referred to as "He."

    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
     experienced
    -0.63
     defaults
    -0.59
     seasoned
    -0.59
     2048
    -0.59
     any
    -0.57
     remed
    -0.57
     public
    -0.57
     pressing
    -0.57
     optional
    -0.56
     discontinued
    -0.56
    POSITIVE LOGITS
    He
    3.04
    His
    2.42
     He
    2.03
    he
    1.72
    She
    1.71
    his
    1.67
     His
    1.54
    HE
    1.49
     he
    1.46
    They
    1.33
    Activations Density 0.028%

    No Known Activations