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. 23652
    Prev
    Next
    INDEX
    Explanations

    adjectives related to time

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "recent" indicating time-related context

    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
    claimer
    -0.80
    hatt
    -0.71
    ynchron
    -0.71
    vantage
    -0.70
    ype
    -0.70
    ifle
    -0.69
    umbledore
    -0.68
    fee
    -0.68
    alach
    -0.66
    vy
    -0.65
    POSITIVE LOGITS
     evenings
    0.97
     editions
    0.92
     spate
    0.90
     developments
    0.88
     controversies
    0.87
     afternoon
    0.86
     occasions
    0.83
     weeks
    0.83
     generations
    0.82
    ebin
    0.82
    Activations Density 0.019%

    No Known Activations