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. 17640
    Prev
    Next
    INDEX
    Explanations

    phrases related to the duration of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the duration of events or experiences

    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
    reci
    -0.70
    rim
    -0.67
    agon
    -0.66
    raised
    -0.66
    alty
    -0.63
    erning
    -0.62
    involved
    -0.61
    ledged
    -0.60
     leveled
    -0.58
    ramid
    -0.57
    POSITIVE LOGITS
    IER
    0.82
     thro
    0.77
     longer
    0.77
     lasting
    0.75
    staking
    0.74
    Duration
    0.73
    stall
    0.71
    ime
    0.69
    inka
    0.69
     satisf
    0.68
    Activations Density 0.015%

    No Known Activations