Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 19215
    Prev
    Next
    INDEX
    Explanations

    phrases related to time duration

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference the passage of time, specifically in relation to the last several years or decades

    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
    ollow
    -0.71
    aband
    -0.70
    hots
    -0.65
    udd
    -0.65
    acers
    -0.64
    obs
    -0.64
    athing
    -0.64
    ingen
    -0.63
    afort
    -0.63
    mbuds
    -0.63
    POSITIVE LOGITS
     decade
    1.15
     ditch
    0.97
     gasp
    0.95
     millennium
    0.94
     month
    0.94
    ebin
    0.91
     week
    0.90
     year
    0.89
     century
    0.88
     installment
    0.88
    Activations Density 0.032%

    No Known Activations