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. 11-RES-JB
    6. 8075
    Prev
    Next
    INDEX
    Explanations

    phrases describing a specific time period, generally focusing on durations like "past two decades" or "last two years"

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, specifically the phrases "past two" and "past three years."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vantage
    -0.72
    vec
    -0.68
    affer
    -0.66
    vale
    -0.65
    eteria
    -0.65
    isky
    -0.64
    angers
    -0.64
    urat
    -0.63
    rium
    -0.63
    wrapper
    -0.62
    POSITIVE LOGITS
     years
    1.37
     decades
    1.35
     summers
    1.28
     seasons
    1.24
     months
    1.23
     weeks
    1.23
     winters
    1.19
     editions
    1.07
     generations
    1.07
     days
    1.04
    Activations Density 0.055%

    No Known Activations