© 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. 1-RES-JB
    11. 3380
    Prev
    Next
    INDEX
    Explanations

    Slavic languages characters and potentially medical terms or associations

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols present in a non-English text, particularly looking for occurrences of the character 'ÑĤ'

    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
     bonded
    -0.71
     preferred
    -0.67
     clutch
    -0.66
     wearable
    -0.65
     unseen
    -0.63
     treadmill
    -0.63
     trusted
    -0.62
    ciating
    -0.61
    thur
    -0.61
     thin
    -0.61
    POSITIVE LOGITS
    ÑĮ
    1.50
    е
    1.48
    н
    1.48
    ÑĢ
    1.44
    Ñĭ
    1.39
    а
    1.38
    Ñģ
    1.37
    о
    1.37
    и
    1.31
    в
    1.27
    Activations Density 0.004%

    No Known Activations