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. 0-RES-JB
    6. 69
    Prev
    Next
    INDEX
    Explanations

    the name "Hernandez" in different contexts and scenarios

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the surname "Hernandez."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CP
    -0.67
     Py
    -0.67
     freeze
    -0.66
    forth
    -0.65
     coal
    -0.63
     mp
    -0.63
     prim
    -0.63
    masters
    -0.60
    Py
    -0.60
     decl
    -0.60
    POSITIVE LOGITS
     Hernandez
    3.99
    ernandez
    1.73
     Herrera
    1.52
     Ortiz
    1.50
     Fernandez
    1.40
     Suarez
    1.39
     Gonzalez
    1.39
     Alonso
    1.35
     Martinez
    1.33
     Rodriguez
    1.31
    Activations Density 0.018%

    No Known Activations