© 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. 3-RES-JB
    11. 590
    Prev
    Next
    INDEX
    Explanations

    words with the letter 'o' where the 'o' is repeated or emphasized, such as 'ooo' or 'ooooooo.'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'o'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glim
    -0.82
    è£
    -0.72
     Shades
    -0.70
     compe
    -0.67
     Avalanche
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
     EntityItem
    -0.65
    ãĥ¼ãĥĨ
    -0.62
     condem
    -0.62
     Pilgrim
    -0.62
    POSITIVE LOGITS
    zzi
    1.33
    zzo
    1.22
    oms
    1.07
    cean
    1.07
    onga
    1.03
    ghan
    1.00
    ichi
    0.98
    vernment
    0.97
    ope
    0.97
    oga
    0.96
    Activations Density 0.044%

    No Known Activations