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. 0-RES-JB
    6. 24298
    Prev
    Next
    INDEX
    Explanations

    word parts associated with the term "arc" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "arc" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kindly
    -0.69
     soak
    -0.65
     irrig
    -0.64
     warming
    -0.64
     fertility
    -0.64
     watering
    -0.64
     Brett
    -0.64
     ratification
    -0.63
     delegation
    -0.62
     seed
    -0.62
    POSITIVE LOGITS
    arc
    4.81
    ARC
    2.25
    Arc
    1.67
    arr
    1.46
    arp
    1.45
     Arc
    1.33
     ARC
    1.30
     arc
    1.30
    arl
    1.12
     Narc
    1.10
    Activations Density 0.008%

    No Known Activations