© 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
    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. 19040
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific name "Doña Pãz"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names or terms related to individuals, particularly in the context of discussing events or actions

    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
    uton
    -0.73
    ocker
    -0.70
     scal
    -0.66
    util
    -0.66
     alloc
    -0.66
     cub
    -0.65
    rolling
    -0.65
     lim
    -0.64
     bri
    -0.64
     cass
    -0.63
    POSITIVE LOGITS
    ña
    1.96
     Emails
    1.93
     Stories
    1.72
    DAY
    1.40
     Lies
    1.24
     Skies
    1.23
     Seasons
    1.21
    enda
    1.09
     Episode
    1.02
     Streets
    1.01
    Activations Density 0.029%

    No Known Activations