© 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. 716
    Prev
    Next
    INDEX
    Explanations

    words related to the sea or bodies of water

    oai_token-act-pair · gpt-3.5-turbo

    references to the sea and its levels

    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
    IBLE
    -0.89
    iom
    -0.83
    etts
    -0.80
    ä½ľ
    -0.78
    ongyang
    -0.78
    cussion
    -0.74
    ivated
    -0.73
    IVES
    -0.73
    iaries
    -0.72
    mination
    -0.72
    POSITIVE LOGITS
     sea
    1.15
     Sea
    1.00
    plane
    0.97
     shore
    0.95
     crocod
    0.93
     lions
    0.92
     monster
    0.87
     ocean
    0.87
    Sea
    0.85
     sharks
    0.84
    Activations Density 0.009%

    No Known Activations