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. 17600
    Prev
    Next
    INDEX
    Explanations

    mentions of sports seasons or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "regular" and its variations in the context of seasons

    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
    lda
    -0.72
     Mb
    -0.68
    ï¸ı
    -0.65
     Kardashian
    -0.63
    UST
    -0.63
    IRO
    -0.63
     Bourbon
    -0.62
    arta
    -0.62
     Shib
    -0.62
    NRS
    -0.61
    POSITIVE LOGITS
    ity
    1.10
    isation
    1.03
    izations
    1.01
    ization
    1.00
    isations
    0.91
    ties
    0.91
     appearances
    0.86
    izing
    0.85
    iated
    0.85
    ITY
    0.85
    Activations Density 0.007%

    No Known Activations