© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2670
    Prev
    Next
    INDEX
    Explanations

    terms related to evolutionary biology and human evolution, particularly focusing on mutations, adaptations, and gene replication

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms and concepts related to evolution and evolutionary biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Territories
    -0.69
    ð
    -0.64
    amina
    -0.62
    dig
    -0.61
    jah
    -0.61
    stra
    -0.60
     Territory
    -0.58
    zes
    -0.58
    este
    -0.58
     throats
    -0.58
    POSITIVE LOGITS
    arily
    1.71
    ary
    1.25
     biologist
    1.10
     biology
    1.06
     biologists
    1.06
    ists
    0.91
    ally
    0.88
    ivist
    0.86
    ist
    0.86
    arian
    0.84
    Activations Density 0.067%

    No Known Activations