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. 0-RES-JB
    6. 3622
    Prev
    Next
    INDEX
    Explanations

    phrases related to waste or items that are deemed unimportant or unwanted

    oai_token-act-pair · gpt-3.5-turbo

    references to trash or waste management

    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
     Meridian
    -0.84
    FE
    -0.74
    eta
    -0.74
     Leeds
    -0.73
     Pyth
    -0.73
     Moore
    -0.72
     arising
    -0.71
     Hert
    -0.71
    BBC
    -0.68
     recognised
    -0.67
    POSITIVE LOGITS
     trash
    3.77
     Trash
    2.71
     garbage
    2.16
     rubbish
    1.92
     recycle
    1.37
     dump
    1.36
     recycling
    1.32
     litter
    1.28
     recy
    1.28
     waste
    1.26
    Activations Density 0.009%

    No Known Activations