© 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. 1-RES-JB
    11. 10276
    Prev
    Next
    INDEX
    Explanations

    numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values, specifically large figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MSN
    -0.79
    href
    -0.76
    lez
    -0.75
     stead
    -0.73
    cho
    -0.72
    ration
    -0.69
    ffield
    -0.67
    imen
    -0.67
    elly
    -0.65
    ravings
    -0.65
    POSITIVE LOGITS
    mAh
    1.05
    8000
    1.03
     8000
    0.89
     6000
    0.89
    6000
    0.87
    4000
    0.83
     7000
    0.82
     5000
    0.81
     4000
    0.81
     9000
    0.80
    Activations Density 0.009%

    No Known Activations