© 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. 11-RES-JB
    11. 10186
    Prev
    Next
    INDEX
    Explanations

    Turkish words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    fragments of words or syllables, likely indicating a focus on language patterns and morphology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rhodes
    -1.06
     Wilmington
    -0.88
     Rouge
    -0.86
     Cruise
    -0.84
     Belle
    -0.83
     Scorp
    -0.83
     Essex
    -0.82
     Blacks
    -0.80
     Charleston
    -0.80
     Windsor
    -0.79
    POSITIVE LOGITS
    ı
    2.18
    ÄŁ
    1.96
    ÅŁ
    1.92
    oÄŁ
    1.56
    stanbul
    1.54
     Ãĸ
    1.49
    ç
    1.46
     Erd
    1.45
    oÄŁan
    1.42
    lar
    1.39
    Activations Density 0.111%

    No Known Activations