© 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. 10-RES-JB
    11. 16110
    Prev
    Next
    INDEX
    Explanations

    phrases related to the consequences and impacts of various global, environmental, and economic issues

    oai_token-act-pair · gpt-3.5-turbo

    references to the effects and consequences of climate change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppa
    -1.04
    thia
    -0.88
    DragonMagazine
    -0.83
    apest
    -0.82
    è£
    -0.80
    istics
    -0.79
    keys
    -0.79
    onyms
    -0.78
    enf
    -0.76
    earchers
    -0.76
    POSITIVE LOGITS
     inaction
    1.25
     globalization
    1.14
     prolonged
    1.06
     neglect
    1.01
     adopting
    1.01
     changing
    0.98
     unchecked
    0.96
     aging
    0.95
     ageing
    0.95
     legalizing
    0.95
    Activations Density 0.182%

    No Known Activations