© 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. 20135
    Prev
    Next
    INDEX
    Explanations

    mentions of the ocean

    oai_token-act-pair · gpt-3.5-turbo

    references to the ocean and its features

    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
    Hack
    -0.82
    lik
    -0.77
     Kut
    -0.74
    VID
    -0.74
     Lyons
    -0.70
     Clubs
    -0.69
    irk
    -0.68
    hack
    -0.67
    Focus
    -0.66
     Whe
    -0.66
    POSITIVE LOGITS
     ocean
    3.51
     Ocean
    2.39
     oceans
    2.34
    Ocean
    2.20
     sea
    2.16
    cean
    1.83
     seas
    1.76
     seaf
    1.69
     iceberg
    1.67
     seaw
    1.63
    Activations Density 0.008%

    No Known Activations