© 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. 2-RES-JB
    6. 12745
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, specifically involving grandparents and great-grandparents

    oai_token-act-pair · gpt-3.5-turbo

    references to "grand" or "great-grand" family relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.84
    tics
    -0.72
    ijk
    -0.65
     Alvarez
    -0.64
     stocks
    -0.64
    ggies
    -0.57
     timely
    -0.57
     specially
    -0.56
    ayers
    -0.56
     warranted
    -0.55
    POSITIVE LOGITS
    father
    1.26
    grand
    1.14
    mother
    1.07
    iosity
    0.98
    parents
    0.97
     Prix
    0.96
    daughter
    0.93
    pa
    0.89
    child
    0.86
    parent
    0.82
    Activations Density 0.003%

    No Known Activations