© 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. 14544
    Prev
    Next
    INDEX
    Explanations

    sentences that end with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express conclusions or definitive statements

    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
     metic
    -0.75
    uly
    -0.68
    iber
    -0.67
    thal
    -0.67
     footing
    -0.66
    onga
    -0.65
     purse
    -0.65
    loo
    -0.64
     tyr
    -0.64
     mosqu
    -0.64
    POSITIVE LOGITS
     However
    0.97
     Additionally
    0.94
     Likewise
    0.90
     Unfortunately
    0.90
     Therefore
    0.90
     Flavoring
    0.88
     They
    0.87
     Specifically
    0.86
     Moreover
    0.86
     Furthermore
    0.86
    Activations Density 1.675%

    No Known Activations