Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 24493
    Prev
    Next
    INDEX
    Explanations

    the letter "о"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "о" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clover
    -0.83
    raints
    -0.76
    esville
    -0.74
    hyde
    -0.73
    orial
    -0.72
    ologically
    -0.71
    ored
    -0.71
    oring
    -0.69
    ibility
    -0.67
     pulp
    -0.66
    POSITIVE LOGITS
    о
    1.37
    е
    1.32
    Ñ
    1.31
    ÑĢ
    1.29
    н
    1.25
    ÑĤ
    1.19
    Ñģ
    1.17
    Ñı
    1.15
    и
    1.14
     Ð
    1.07
    Activations Density 0.004%

    No Known Activations