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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 4125
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotions, especially focusing on feelings and thoughts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of feelings and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ature
    -0.67
    GE
    -0.65
     Mb
    -0.65
    GH
    -0.64
    lite
    -0.64
     supplement
    -0.62
     supplemented
    -0.62
    anned
    -0.61
    lete
    -0.61
    jan
    -0.61
    POSITIVE LOGITS
     feelings
    3.68
     emotions
    2.25
     sentiments
    2.14
     feeling
    1.80
     sensations
    1.73
     thoughts
    1.66
     memories
    1.63
    feel
    1.57
     sensibilities
    1.56
     frustrations
    1.54
    Activations Density 0.007%

    No Known Activations