Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 18442
    Prev
    Next
    INDEX
    Explanations

    information related to historical figures and family relationships

    oai_token-act-pair · gpt-3.5-turbo

    historical figures and their familial or marital connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     takedown
    -0.83
     Clicker
    -0.76
     Spotlight
    -0.73
     analytics
    -0.72
     lasers
    -0.72
     Tactical
    -0.69
     OPEN
    -0.68
    iasco
    -0.68
     Yelp
    -0.68
     cybersecurity
    -0.67
    POSITIVE LOGITS
     descendants
    1.47
     eldest
    1.47
     offspring
    1.43
     hereditary
    1.41
     heirs
    1.38
     inherit
    1.38
     daughters
    1.35
     heir
    1.35
     grandchildren
    1.33
    iblings
    1.32
    Activations Density 0.625%

    No Known Activations