© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 15408
    Prev
    Next
    INDEX
    Explanations

    terms related to family relationships and lineage

    oai_token-act-pair · gpt-3.5-turbo

    terms related to maternal and paternal identities and family roles

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

    No Comments

    Negative Logits
     Flavoring
    -0.93
    heimer
    -0.81
    umbn
    -0.75
     Heist
    -0.73
    yz
    -0.73
    xxxxxxxx
    -0.73
    Sean
    -0.73
    Rush
    -0.73
    =-=-=-=-
    -0.72
    é¾
    -0.71
    POSITIVE LOGITS
     mothers
    0.86
     maternal
    0.83
     moms
    0.78
    ignt
    0.78
    aternal
    0.77
     stagn
    0.77
     parental
    0.74
     infertility
    0.72
     grandparents
    0.72
     care
    0.71
    Activations Density 0.020%

    No Known Activations