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. 6015
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, specifically focusing on sons

    oai_token-act-pair · gpt-3.5-turbo

    references to family members, specifically daughters and sons

    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
     user
    -0.72
     User
    -0.68
     NPC
    -0.67
     Expert
    -0.65
     Butterfly
    -0.64
    EVA
    -0.64
    User
    -0.63
     VR
    -0.62
    affe
    -0.62
    ello
    -0.62
    POSITIVE LOGITS
     sons
    3.41
     daughters
    2.62
     Sons
    2.17
     wives
    1.78
     husbands
    1.76
     brothers
    1.75
     heirs
    1.73
     grandchildren
    1.72
     fathers
    1.67
     boys
    1.66
    Activations Density 0.014%

    No Known Activations