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. 1-RES-JB
    6. 15045
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvement or optimization

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Better."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eur
    -0.70
    orial
    -0.69
    verson
    -0.68
    wart
    -0.67
    trl
    -0.67
    htar
    -0.66
    ãĤ·ãĥ£
    -0.66
    ãĥĢ
    -0.65
    LS
    -0.64
    MIT
    -0.63
    POSITIVE LOGITS
     Better
    1.23
    Better
    1.00
     Faster
    0.88
     Than
    0.85
     Advice
    0.80
     Quality
    0.75
     Neigh
    0.74
     Worse
    0.74
     Rivals
    0.74
    luaj
    0.73
    Activations Density 0.008%

    No Known Activations