© 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. 11-RES-JB
    11. 24456
    Prev
    Next
    INDEX
    Explanations

    error-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to error handling in programming, particularly in Python

    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
    jen
    -0.76
     Mechdragon
    -0.70
    sonian
    -0.68
     ambitions
    -0.68
    electric
    -0.67
    airo
    -0.64
    Electric
    -0.64
     aspirations
    -0.63
     Aires
    -0.62
     Fathers
    -0.62
    POSITIVE LOGITS
     message
    1.03
     messages
    0.99
    Msg
    0.96
     handler
    0.94
    prone
    0.92
    Message
    0.91
     propagation
    0.90
     propagate
    0.90
     Handling
    0.89
    message
    0.88
    Activations Density 0.073%

    No Known Activations