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. 9-RES-JB
    6. 18977
    Prev
    Next
    INDEX
    Explanations

    references to adjustments or adaptations in different aspects of life

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to life experiences and adjustments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     induct
    -0.79
     theorem
    -0.78
     Citation
    -0.75
     thesis
    -0.71
     reprint
    -0.68
     fallacy
    -0.67
     nominate
    -0.67
     grant
    -0.65
     deduction
    -0.65
     patents
    -0.64
    POSITIVE LOGITS
     pandemonium
    0.96
    quiet
    0.95
    iences
    0.94
     happier
    0.93
     life
    0.93
     smoother
    0.92
     paradise
    0.91
    pleasant
    0.90
    normal
    0.90
     liv
    0.89
    Activations Density 1.238%

    No Known Activations