© 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. 2167
    Prev
    Next
    INDEX
    Explanations

    phrases relating to the advantages and disadvantages of different subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of contrasting elements, particularly pros and cons

    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
    SOURCE
    -0.79
    enegger
    -0.78
    ONSORED
    -0.78
    STER
    -0.73
    pointer
    -0.72
    ĸļ
    -0.72
    aste
    -0.70
    older
    -0.69
    wolf
    -0.68
    signed
    -0.66
    POSITIVE LOGITS
     valleys
    1.10
     downs
    0.97
     lows
    0.96
     oranges
    0.96
     bounds
    0.95
     bolts
    0.93
     pains
    0.89
     dips
    0.88
    adders
    0.87
     bruises
    0.86
    Activations Density 0.091%

    No Known Activations