© 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. 7-RES-JB
    11. 2907
    Prev
    Next
    INDEX
    Explanations

    water-related entities and marine-life terms

    oai_token-act-pair · gpt-3.5-turbo

    references to marine life and ecosystems, particularly coral reefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Madison
    -0.76
    ENT
    -0.72
    Machine
    -0.72
    UGC
    -0.71
    TI
    -0.71
     CBI
    -0.71
     Eliot
    -0.71
    Interstitial
    -0.70
    GV
    -0.68
    ãĤ¤ãĥĪ
    -0.68
    POSITIVE LOGITS
     reefs
    1.30
     reef
    1.27
     aquarium
    0.99
     Reef
    0.99
     habitat
    0.87
     coral
    0.80
    fish
    0.80
    odon
    0.78
     canopy
    0.77
    arium
    0.77
    Activations Density 0.024%

    No Known Activations