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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 19359
    Prev
    Next
    INDEX
    Explanations

    verbs related to wasting time or resources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wasted" and related terms indicating misuse or squandering of time or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mandarin
    -0.68
    ylum
    -0.65
    enge
    -0.64
     Accord
    -0.64
    ears
    -0.63
    ector
    -0.63
    actionDate
    -0.62
     Protocol
    -0.61
    oké
    -0.60
     tune
    -0.60
    POSITIVE LOGITS
     wasted
    3.57
     wasting
    2.65
     wastes
    1.77
     waste
    1.76
     wasteful
    1.59
     wast
    1.55
     needless
    1.31
     Waste
    1.29
     useless
    1.26
     pointless
    1.18
    Activations Density 0.027%

    No Known Activations