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. 11-RES-JB
    6. 7941
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic similarities and differences between humans and other animals

    oai_token-act-pair · gpt-3.5-turbo

    references to evolutionary relationships among species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    INESS
    -0.91
    ettings
    -0.82
    antage
    -0.82
    iversary
    -0.82
    essional
    -0.82
    inventoryQuantity
    -0.81
    soType
    -0.79
    ãĤ¢ãĥ«
    -0.78
    Quality
    -0.77
    imity
    -0.76
    POSITIVE LOGITS
     primates
    1.98
     chimpanzees
    1.92
     mammals
    1.91
     humans
    1.79
     apes
    1.78
     monkeys
    1.66
     mammalian
    1.61
     rodents
    1.58
     chimpan
    1.57
     Homo
    1.54
    Activations Density 0.299%

    No Known Activations