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. 3435
    Prev
    Next
    INDEX
    Explanations

    references to the programming language "Java."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the programming language Java

    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
    Ð
    -0.67
    lev
    -0.63
     pump
    -0.62
     expend
    -0.61
    iev
    -0.61
    shaw
    -0.61
    odies
    -0.61
    sle
    -0.60
    agher
    -0.60
    eur
    -0.59
    POSITIVE LOGITS
     Java
    3.59
    Java
    2.75
     java
    2.04
    java
    1.99
     Scala
    1.86
     Clojure
    1.74
     Jakarta
    1.70
     JavaScript
    1.54
     Indonesia
    1.48
     JD
    1.47
    Activations Density 0.014%

    No Known Activations