Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18314
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "Don't" or "Don't" contracted

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "don't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     logger
    -0.61
    etheless
    -0.60
     Tsuk
    -0.60
     Pwr
    -0.60
     freed
    -0.59
    aminer
    -0.59
     cyan
    -0.58
     buggy
    -0.58
    terday
    -0.56
     missed
    -0.56
    POSITIVE LOGITS
    oso
    0.80
    action
    0.75
    _>
    0.75
    sylvania
    0.75
    istan
    0.69
    thood
    0.69
    rio
    0.67
    ship
    0.67
    abo
    0.66
    uum
    0.65
    Activations Density 0.208%

    No Known Activations