Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8653
    Prev
    Next
    INDEX
    Explanations

    negative emotions and sentiments related to guilt, sadness, and insecurity

    oai_token-act-pair · gpt-3.5-turbo

    expressions of negative emotions and states of mind

    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
    uria
    -0.70
     defic
    -0.65
    arcity
    -0.60
     Tobacco
    -0.60
    eatures
    -0.60
    Explore
    -0.58
    eu
    -0.58
     Provided
    -0.57
    utions
    -0.57
     vantage
    -0.57
    POSITIVE LOGITS
     ABOUT
    1.25
     about
    1.25
     bc
    1.06
     wondering
    1.04
     thinking
    0.96
     About
    0.96
     imagining
    0.94
    about
    0.94
     watching
    0.91
     because
    0.88
    Activations Density 0.265%

    No Known Activations