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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3324
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to be looking for a specific pattern of characters or words that don't conform to any recognizable language or structure

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols, potentially from various languages or encoding systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bonded
    -0.78
    cius
    -0.76
     flour
    -0.75
     biod
    -0.73
     bour
    -0.73
     dominated
    -0.73
     rigged
    -0.73
     centrally
    -0.71
     glossy
    -0.71
     polyg
    -0.70
    POSITIVE LOGITS
    ãģŁ
    1.86
    ãģ¦
    1.82
    ãģĦ
    1.81
    ãģ¾
    1.81
    ãĤĭ
    1.80
    ãĤ
    1.78
    ãģ
    1.75
    ãģª
    1.75
    ãĢģ
    1.72
    ãģ§
    1.71
    Activations Density 0.019%

    No Known Activations