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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2-RES-JB
    6. 16219
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, specifically siblings

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships, specifically siblings

    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
    vasive
    -0.71
    atana
    -0.67
    osph
    -0.64
    inen
    -0.64
    xtap
    -0.63
     Woman
    -0.62
    iasis
    -0.62
    ajo
    -0.62
    arted
    -0.62
    cers
    -0.62
    POSITIVE LOGITS
     siblings
    1.16
     sibling
    0.97
    iblings
    0.81
     twins
    0.80
    ibling
    0.79
    wcsstore
    0.78
    riages
    0.76
    ilial
    0.75
     Inher
    0.73
     adolesc
    0.72
    Activations Density 0.018%

    No Known Activations