© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 4900
    Prev
    Next
    INDEX
    Explanations

    words related to fuels, particularly biofuels

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to environmental and health hazards, specifically focusing on biofuels and toxic substances

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

    No Comments

    Negative Logits
    iple
    -0.74
    ellation
    -0.69
    APS
    -0.67
     Canter
    -0.66
    WN
    -0.65
    âĸ¬
    -0.65
     Clement
    -0.64
     Cind
    -0.64
    AMS
    -0.63
     Avalon
    -0.63
    POSITIVE LOGITS
    ervative
    0.90
     warfare
    0.81
    osate
    0.80
    ervatives
    0.76
    mong
    0.74
     poisoning
    0.74
     Warfare
    0.72
    amphetamine
    0.69
    aceutical
    0.68
    afety
    0.68
    Activations Density 0.127%

    No Known Activations