© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 1182
    Prev
    Next
    INDEX
    Explanations

    Turkish letters with diacritics

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or encoding-related anomalies, particularly around the character "ı"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scarlet
    -0.81
     MS
    -0.75
     hearts
    -0.68
     Legacy
    -0.67
     Phil
    -0.66
     Kenn
    -0.65
     Kent
    -0.64
     seam
    -0.63
     Cass
    -0.63
     ACC
    -0.63
    POSITIVE LOGITS
    ı
    4.41
    ÄŁ
    2.33
    oÄŁ
    1.70
    ÅŁ
    1.65
    oÄŁan
    1.61
    stanbul
    1.52
     Ankara
    1.50
     Ãĸ
    1.47
    Turkish
    1.42
     PKK
    1.37
    Activations Density 0.013%

    No Known Activations