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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 19550
    Prev
    Next
    INDEX
    Explanations

    specific instances or events

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "there was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arta
    -0.83
    owe
    -0.73
    mare
    -0.72
    lish
    -0.65
    coin
    -0.62
    otic
    -0.62
    anium
    -0.61
     ®
    -0.60
    allows
    -0.60
    Nation
    -0.59
    POSITIVE LOGITS
     pandemonium
    0.91
     uproar
    0.83
    emonium
    0.80
     murm
    0.77
    OOL
    0.73
     outcry
    0.72
     reluct
    0.71
    hes
    0.70
     plenty
    0.67
     whispers
    0.65
    Activations Density 0.089%

    No Known Activations