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. 1-RES-JB
    6. 11977
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Lin" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Lin" and its variations or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburgh
    -0.75
     Seym
    -0.66
    illed
    -0.65
    raints
    -0.63
    代
    -0.62
     JUSTICE
    -0.61
     bald
    -0.61
    raltar
    -0.61
    ATTLE
    -0.60
     McKay
    -0.60
    POSITIVE LOGITS
     Lin
    0.97
    Lin
    0.96
    eman
    0.94
    emate
    0.93
    iets
    0.90
    ergic
    0.89
    ergy
    0.87
    sei
    0.82
    olen
    0.80
    nette
    0.80
    Activations Density 0.006%

    No Known Activations