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. 20293
    Prev
    Next
    INDEX
    Explanations

    mentions of buckets

    oai_token-act-pair · gpt-3.5-turbo

    references to "buckets."

    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
     Examiner
    -0.76
    ournal
    -0.75
    mercial
    -0.65
    enegger
    -0.64
    onduct
    -0.62
    uality
    -0.60
    ocard
    -0.60
    ORE
    -0.60
    nda
    -0.60
    egal
    -0.59
    POSITIVE LOGITS
     bucket
    1.18
     buckets
    1.13
     Bucket
    1.05
    buck
    0.85
    pipe
    0.82
    wagon
    0.79
     Rapids
    0.79
    chest
    0.79
    iatus
    0.74
    ucket
    0.74
    Activations Density 0.005%

    No Known Activations