© 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. 11-RES-JB
    11. 9087
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to experiences or activities

    oai_token-act-pair · gpt-3.5-turbo

    emotions and personal reflections related to life experiences

    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
    Names
    -0.80
    orem
    -0.78
     Cosponsors
    -0.75
    orsi
    -0.73
    PLA
    -0.72
     Specifications
    -0.72
    idth
    -0.72
     Actress
    -0.70
     Designs
    -0.69
     STATS
    -0.67
    POSITIVE LOGITS
     stressful
    1.59
     rewarding
    1.56
     exhausting
    1.55
     liberating
    1.52
     exhilar
    1.51
     enjoyable
    1.46
     relaxing
    1.37
     fulfilling
    1.34
     unbearable
    1.24
     satisfying
    1.23
    Activations Density 0.393%

    No Known Activations