© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 17391
    Prev
    Next
    INDEX
    Explanations

    the Cyrillic character "о"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character or 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
     Clover
    -0.92
    esville
    -0.89
    ometimes
    -0.83
    nesday
    -0.82
    ologically
    -0.79
    hyde
    -0.78
    secut
    -0.71
    raints
    -0.71
    imilar
    -0.67
    arton
    -0.67
    POSITIVE LOGITS
    ÑĢ
    1.12
    н
    1.12
    Ñģ
    1.11
    ÑĤ
    1.11
    Ñ
    1.10
    е
    1.04
    о
    0.96
     Ð
    0.95
    Ì
    0.93
    и
    0.92
    Activations Density 0.005%

    No Known Activations