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. 6-RES-JB
    6. 16298
    Prev
    Next
    INDEX
    Explanations

    keywords related to someone or something coming back or returning

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "back."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.65
     Strait
    -0.63
    "]=>
    -0.62
    entric
    -0.61
    enaries
    -0.59
     CCP
    -0.59
     Sorceress
    -0.59
     delegation
    -0.58
    inational
    -0.58
     viz
    -0.58
    POSITIVE LOGITS
    tracking
    1.15
    GROUND
    1.07
    dated
    1.04
    packs
    0.93
    ordered
    0.92
    dating
    0.89
    ported
    0.88
    ped
    0.87
    home
    0.87
    loaded
    0.87
    Activations Density 0.033%

    No Known Activations