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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 9858
    Prev
    Next
    INDEX
    Explanations

    family-related terms, specifically related to maternal and paternal lineage

    oai_token-act-pair · gpt-3.5-turbo

    terms related to familial relationships and lineage, particularly maternal and paternal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yers
    -0.90
    lins
    -0.88
    âĸ¬
    -0.77
    Journal
    -0.77
    oria
    -0.77
    yre
    -0.76
    eller
    -0.74
    Ĥ¬
    -0.72
    riz
    -0.72
    Week
    -0.71
    POSITIVE LOGITS
     paternal
    1.24
     maternal
    1.00
    aternal
    0.86
    istically
    0.86
    volent
    0.84
     ancestor
    0.75
    istic
    0.74
    conservancy
    0.74
    otin
    0.73
     gobl
    0.73
    Activations Density 0.008%

    No Known Activations