© 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. 0-RES-JB
    11. 1599
    Prev
    Next
    INDEX
    Explanations

    phrases or sequences of text containing the word "ao" with varying activation strengths

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the particle "ao" which appears to be heavily weighted throughout the text

    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
     Slug
    -0.78
     Vers
    -0.74
     installations
    -0.67
     recept
    -0.66
     financially
    -0.65
     Cascade
    -0.63
     Schl
    -0.63
     plugs
    -0.62
     Slam
    -0.62
     sticker
    -0.61
    POSITIVE LOGITS
    ao
    4.61
    ão
    1.91
    iao
    1.53
    aos
    1.46
     Tao
    1.45
    ai
    1.30
    uan
    1.29
    ui
    1.29
    uo
    1.28
    afa
    1.26
    Activations Density 0.012%

    No Known Activations