© 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. 9470
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and well-being, especially with regards to homelessness and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to health and well-being challenges

    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
    quished
    -0.72
    uously
    -0.72
     Cosponsors
    -0.65
     Nare
    -0.64
    mire
    -0.63
    wic
    -0.62
    mad
    -0.62
     Lange
    -0.61
    umerable
    -0.61
    signed
    -0.61
    POSITIVE LOGITS
     wellbeing
    1.36
     productivity
    1.23
     longevity
    1.23
     stability
    1.22
     effectiveness
    1.22
     efficiency
    1.22
     viability
    1.18
     performance
    1.18
     reliability
    1.18
     competitiveness
    1.16
    Activations Density 0.703%

    No Known Activations