© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11995
    Prev
    Next
    INDEX
    Explanations

    mentions of oceans or seas

    oai_token-act-pair · gpt-3.5-turbo

    references to seas and bodies of water

    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
     MFT
    -0.77
     Feldman
    -0.66
     ML
    -0.66
    mination
    -0.65
     Attribution
    -0.62
    object
    -0.62
    Document
    -0.61
     Illum
    -0.60
    handler
    -0.59
    eteria
    -0.59
    POSITIVE LOGITS
     seas
    4.02
     Seas
    2.82
     waters
    1.52
     oceans
    1.43
     sea
    1.35
     skies
    1.32
     seaf
    1.30
     rivers
    1.27
     seaw
    1.26
     Sea
    1.25
    Activations Density 0.007%

    No Known Activations