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. 19708
    Prev
    Next
    INDEX
    Explanations

    time-related events that happened in the past

    oai_token-act-pair · gpt-3.5-turbo

    references to time, specifically events that occurred in the past

    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
     Scully
    -0.66
    nce
    -0.64
     Cipher
    -0.64
     Scal
    -0.64
     Sph
    -0.61
     Gad
    -0.59
    icular
    -0.59
     Stellar
    -0.58
     Trou
    -0.57
    anium
    -0.57
    POSITIVE LOGITS
     earthqu
    0.85
     mosqu
    0.82
     apiece
    0.81
     nomine
    0.76
     nodd
    0.73
    apon
    0.71
    nown
    0.70
     eleph
    0.70
     conflic
    0.68
    ivari
    0.65
    Activations Density 0.057%

    No Known Activations