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. 15650
    Prev
    Next
    INDEX
    Explanations

    surnames, particularly of Hispanic origin

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and surnames

    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
    krit
    -0.83
    owment
    -0.78
    ERAL
    -0.76
    onyms
    -0.76
    ply
    -0.75
    inburgh
    -0.73
    wegian
    -0.73
    account
    -0.73
    patient
    -0.71
    ship
    -0.70
    POSITIVE LOGITS
     Nieto
    1.58
     Rivera
    1.49
     Flores
    1.46
     Gonzalez
    1.44
     Gomez
    1.43
     Ramos
    1.42
     Martinez
    1.42
     Garcia
    1.42
     Perez
    1.40
     Gutierrez
    1.39
    Activations Density 0.181%

    No Known Activations