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. 6-RES-JB
    6. 23611
    Prev
    Next
    INDEX
    Explanations

    mentions of relationships between people, specifically involving daughters

    oai_token-act-pair · gpt-3.5-turbo

    references to "daughter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constitu
    -0.81
    ilitarian
    -0.74
    kefeller
    -0.72
     Tribunal
    -0.72
    querque
    -0.69
    etting
    -0.67
     dstg
    -0.65
    tering
    -0.65
    psey
    -0.64
     freight
    -0.64
    POSITIVE LOGITS
     Ivanka
    1.02
     Louise
    0.87
     Isabel
    0.85
     daughter
    0.80
    Anne
    0.79
     daughters
    0.79
    hood
    0.78
    Maria
    0.78
     Hannah
    0.78
     Bei
    0.77
    Activations Density 0.017%

    No Known Activations