© 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. 11-RES-JB
    6. 1420
    Prev
    Next
    INDEX
    Explanations

    mentions of familial relationships and connections between individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of familial relationships and connections to well-known individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izons
    -0.67
    Against
    -0.67
    rums
    -0.64
     unprepared
    -0.64
     unaccompanied
    -0.62
    CHECK
    -0.61
     alerts
    -0.61
     electronically
    -0.60
    ILLE
    -0.60
    sites
    -0.59
    POSITIVE LOGITS
     fame
    1.13
     whom
    0.93
     who
    0.88
     founder
    0.88
     ancestor
    0.87
     patriarch
    0.85
     billionaire
    0.85
     dynasty
    0.81
     deceased
    0.81
     fortune
    0.79
    Activations Density 0.428%

    No Known Activations