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. 6-RES-JB
    6. 12473
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to events or actions that have occurred before a particular point in time

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "before that" and variations of it in the context of sequences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.77
     Meaning
    -0.67
    Tan
    -0.64
    icons
    -0.64
    ãĥĸ
    -0.62
    ographies
    -0.62
    istries
    -0.62
     Parables
    -0.61
    Ore
    -0.60
    ELY
    -0.60
    POSITIVE LOGITS
     pesky
    0.96
     fateful
    0.85
    erker
    0.75
     gaping
    0.74
    chery
    0.74
     settles
    0.73
    emetery
    0.72
     sucker
    0.72
     ordeal
    0.72
     initial
    0.70
    Activations Density 0.064%

    No Known Activations