© 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. 0-RES-JB
    11. 1481
    Prev
    Next
    INDEX
    Explanations

    words related to waves or sequences of events

    oai_token-act-pair · gpt-3.5-turbo

    references to waves, particularly in contexts discussing societal or environmental phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ingredients
    -0.70
    parents
    -0.68
    COR
    -0.68
    quartered
    -0.65
    Dex
    -0.63
    imon
    -0.63
     Parenthood
    -0.63
     Veter
    -0.62
     è£ıè
    -0.62
    classified
    -0.62
    POSITIVE LOGITS
     wave
    3.99
     waves
    2.87
    wave
    2.64
     Wave
    2.43
    waves
    2.06
    Wave
    2.04
     Waves
    1.89
     tide
    1.59
     surge
    1.52
     tsunami
    1.40
    Activations Density 0.004%

    No Known Activations