© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 6556
    Prev
    Next
    INDEX
    Explanations

    references to error handling and exceptions in coding

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to programming errors and exceptions 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
    mega
    -0.82
    pins
    -0.75
    chool
    -0.73
     affordability
    -0.72
    æ©
    -0.71
     partnerships
    -0.71
    conom
    -0.69
    nexus
    -0.66
    plates
    -0.66
    vill
    -0.65
    POSITIVE LOGITS
    Error
    1.56
     error
    1.50
    error
    1.49
     Error
    1.43
     abort
    1.39
     ERROR
    1.38
     Errors
    1.32
    Exception
    1.30
     errors
    1.29
    errors
    1.24
    Activations Density 0.302%

    No Known Activations