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. 5958
    Prev
    Next
    INDEX
    Explanations

    terms or actions related to translation or conversion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "translate" or its variations, suggesting a focus on concepts related to translation

    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
    andy
    -0.73
     Brist
    -0.67
    raine
    -0.64
     jo
    -0.64
    ulton
    -0.63
     carpet
    -0.62
     Sandy
    -0.62
    ucc
    -0.62
    reck
    -0.61
    ces
    -0.61
    POSITIVE LOGITS
     translate
    3.70
     translated
    3.50
     translating
    3.04
     translates
    2.86
     translation
    2.40
    translation
    2.31
     translations
    2.26
     Translation
    2.24
     translator
    2.22
    Translation
    2.15
    Activations Density 0.022%

    No Known Activations