© 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. 11-RES-JB
    6. 456
    Prev
    Next
    INDEX
    Explanations

    mentions related to a significant event or crisis, specifically related to the water crisis in Flint, Michigan

    oai_token-act-pair · gpt-3.5-turbo

    references to the Flint water crisis and related political implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EVE
    -0.90
     Allaah
    -0.88
     Leia
    -0.87
    selage
    -0.84
    76561
    -0.83
     Bj
    -0.80
     Spac
    -0.80
    Aust
    -0.79
     Rey
    -0.78
     Cosmos
    -0.76
    POSITIVE LOGITS
     Flint
    2.04
     Snyder
    1.28
     poisoned
    1.28
    nyder
    1.23
     corrosion
    1.19
     poisoning
    1.17
     bottled
    1.16
     fluor
    1.15
     fluoride
    1.14
     arsenic
    1.12
    Activations Density 0.097%

    No Known Activations