© 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. 10-RES-JB
    11. 21442
    Prev
    Next
    INDEX
    Explanations

    specific symbols or characters in text

    oai_token-act-pair · gpt-3.5-turbo

    variations of a specific character or symbol used in text

    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
     burgeoning
    -0.71
     literacy
    -0.68
     recycling
    -0.66
     succession
    -0.64
     Wilmington
    -0.64
     pyramid
    -0.63
     takeaway
    -0.62
     funnel
    -0.62
     unden
    -0.62
     paperback
    -0.61
    POSITIVE LOGITS
    ï¸ı
    1.48
    âĶĢâĶĢâĶĢâĶĢ
    1.19
    à¼
    1.07
    âĸł
    1.07
    £
    1.00
    âĻ
    0.99
    âĢ
    0.97
    о
    0.97
    ¯¯
    0.96
    \'
    0.95
    Activations Density 0.239%

    No Known Activations