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. 9-RES-JB
    6. 861
    Prev
    Next
    INDEX
    Explanations

    the word "eventually"

    oai_token-act-pair · gpt-3.5-turbo

    the word "eventually" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lua
    -0.88
    yet
    -0.75
    VK
    -0.70
    ijk
    -0.63
    tick
    -0.63
    EO
    -0.62
    artisan
    -0.62
    hander
    -0.61
    ocker
    -0.59
    bah
    -0.59
    POSITIVE LOGITS
     succumbed
    0.95
     relent
    0.86
     succumb
    0.86
     overcame
    0.85
     culmin
    0.84
     culminating
    0.84
     reconcil
    0.82
     dwind
    0.81
     settle
    0.81
     culminated
    0.80
    Activations Density 0.043%

    No Known Activations