© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 14426
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Doña Paz."

    oai_token-act-pair · gpt-3.5-turbo

    the character sequence "ña" in names

    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
    ovie
    -0.86
    nostic
    -0.76
    sonian
    -0.75
    spe
    -0.71
    ologies
    -0.71
    ory
    -0.71
    ometric
    -0.70
     Tycoon
    -0.69
    ORY
    -0.69
    points
    -0.68
    POSITIVE LOGITS
    ña
    1.63
     Nieto
    1.47
    ño
    0.98
    ñ
    0.91
     Herrera
    0.87
    án
    0.81
    ÃŃa
    0.74
    ignt
    0.73
     Calder
    0.73
     Cruz
    0.72
    Activations Density 0.014%

    No Known Activations