© 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. 2-RES-JB
    11. 1659
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and technical terms, such as variable names and code structures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the currency symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulative
    -0.76
     Gutenberg
    -0.74
    emonium
    -0.73
    gdala
    -0.69
    enegger
    -0.67
     Spiel
    -0.67
     Addiction
    -0.66
    ropolitan
    -0.65
     Occupations
    -0.64
    hemat
    -0.62
    POSITIVE LOGITS
    ¢
    1.16
    ĥ
    1.05
    ĭ
    0.98
    ¨
    0.96
    «
    0.96
    İ
    0.95
    ¦
    0.94
    §
    0.90
    ķ
    0.89
    º
    0.89
    Activations Density 0.005%

    No Known Activations