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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 10579
    Prev
    Next
    INDEX
    Explanations

    text related to being busy or being occupied with various tasks or activities

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "busy."

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

    No Comments

    Negative Logits
     fullest
    -0.66
    BuyableInstoreAndOnline
    -0.63
    âĵĺ
    -0.63
    arium
    -0.60
    INAL
    -0.59
     Veter
    -0.59
    otide
    -0.59
    Merit
    -0.57
     Racial
    -0.56
    raviolet
    -0.56
    POSITIVE LOGITS
    kson
    0.95
     schedules
    0.83
    bus
    0.79
     intersections
    0.75
    body
    0.74
    tops
    0.74
    ming
    0.74
    agascar
    0.73
    stre
    0.73
     busy
    0.73
    Activations Density 0.015%

    No Known Activations