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. 12843
    Prev
    Next
    INDEX
    Explanations

    mentions of being busy

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "busy" in various contexts

    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
     fullest
    -0.70
    INAL
    -0.66
     Veter
    -0.64
    Merit
    -0.62
    BuyableInstoreAndOnline
    -0.62
     Racial
    -0.61
    arium
    -0.60
     magnitude
    -0.59
    âĵĺ
    -0.58
     Pillar
    -0.58
    POSITIVE LOGITS
    kson
    0.89
    bus
    0.86
     schedules
    0.84
    ming
    0.81
    body
    0.80
    ness
    0.74
    cape
    0.73
     busy
    0.72
    foot
    0.72
     jugg
    0.71
    Activations Density 0.025%

    No Known Activations