© 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. 3541
    Prev
    Next
    INDEX
    Explanations

    words related to water movement or disturbance, particularly waves

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of waves, including sound waves and ocean waves

    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
    ioch
    -0.74
    isma
    -0.70
    orate
    -0.70
    aples
    -0.68
     proc
    -0.68
    uments
    -0.65
    ria
    -0.65
    rax
    -0.64
     reason
    -0.64
     purpose
    -0.62
    POSITIVE LOGITS
     waves
    1.32
    waves
    1.29
     Waves
    1.07
     wave
    1.04
    wave
    1.03
    hower
    0.99
     Wave
    0.96
    hips
    0.85
    guide
    0.85
    imilar
    0.82
    Activations Density 0.009%

    No Known Activations