© 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. 8-RES-JB
    11. 17840
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental disasters, specifically focusing on the Deepwater Horizon oil spill

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic features and locations associated with the Deepwater Horizon incident

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sheet
    -0.80
    leaders
    -0.78
    liam
    -0.75
    Äĩ
    -0.75
    hered
    -0.73
    agher
    -0.73
    ello
    -0.73
     compuls
    -0.72
    ULE
    -0.72
    alysed
    -0.72
    POSITIVE LOGITS
     Ventures
    0.89
     Trail
    0.88
     Armory
    0.86
     Hills
    0.85
     Oaks
    0.85
     Park
    0.84
     Beach
    0.84
     Express
    0.83
     Nights
    0.83
     Horizon
    0.83
    Activations Density 0.111%

    No Known Activations