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. 2-RES-JB
    6. 16919
    Prev
    Next
    INDEX
    Explanations

    words related to sobriety and alertness

    oai_token-act-pair · gpt-3.5-turbo

    references to sobriety and the concept of being awake or aware

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTS
    -0.81
    wei
    -0.77
     Noir
    -0.73
    ADS
    -0.71
    ILA
    -0.70
    tein
    -0.69
    pmwiki
    -0.69
    yip
    -0.68
    ouf
    -0.65
     Rou
    -0.64
    POSITIVE LOGITS
     sober
    1.13
    ing
    0.86
    furt
    0.85
    manship
    0.81
    wallet
    0.76
    ness
    0.76
    entimes
    0.75
    ards
    0.72
    cohol
    0.70
    ly
    0.69
    Activations Density 0.007%

    No Known Activations