© 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. 2-RES-JB
    11. 17544
    Prev
    Next
    INDEX
    Explanations

    the letter "ç" in Portuguese text

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "acción" or similar phonetic elements in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mileage
    -0.77
     gestation
    -0.71
     mutual
    -0.71
     mamm
    -0.69
    packing
    -0.69
     marrow
    -0.68
     fertility
    -0.68
     rooting
    -0.67
     benefic
    -0.66
    ACTED
    -0.64
    POSITIVE LOGITS
    ão
    1.32
    ç
    1.31
    ã
    1.10
    ón
    1.04
    án
    0.94
    uration
    0.93
    illi
    0.91
    Ãĥ
    0.90
    Ã
    0.89
    ez
    0.89
    Activations Density 0.006%

    No Known Activations