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. 7-RES-JB
    6. 18222
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, particularly the presence of children

    oai_token-act-pair · gpt-3.5-turbo

    references to children and parental relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioxide
    -0.76
    pmwiki
    -0.74
    âĸ¬
    -0.69
     metic
    -0.67
     prevailing
    -0.64
     nerve
    -0.64
    ãĥ¢
    -0.61
    TERN
    -0.60
     Coliseum
    -0.59
     guiActiveUnfocused
    -0.58
    POSITIVE LOGITS
    riages
    1.00
     grandchildren
    0.92
    romeda
    0.83
     inherit
    0.81
     eldest
    0.78
    arten
    0.78
     daughters
    0.78
    mares
    0.77
     orphans
    0.76
    iblings
    0.75
    Activations Density 0.084%

    No Known Activations