© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 2563
    Prev
    Next
    INDEX
    Explanations

    Russian words or characters, specifically focusing on the letter "Е" and related variants

    oai_token-act-pair · gpt-3.5-turbo

    Cyrillic characters, particularly the letter 'e' and 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
    accompanied
    -0.81
    arsity
    -0.79
    raints
    -0.75
    usc
    -0.74
    ient
    -0.73
    ommel
    -0.71
    istically
    -0.71
    ajo
    -0.70
    angers
    -0.69
    ored
    -0.69
    POSITIVE LOGITS
    е
    1.48
    н
    1.38
    м
    1.32
    Ñ
    1.31
    ÑĤ
    1.28
    ÑĢ
    1.27
    Ñı
    1.25
    в
    1.22
    Ð
    1.21
    к
    1.20
    Activations Density 0.004%

    No Known Activations