© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 754
    Prev
    Next
    INDEX
    Explanations

    translations or mentions related to the act or process of translating between languages

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "translation" and its variants

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

    No Comments

    Negative Logits
    --+
    -0.89
    oeuv
    -0.81
    ndra
    -0.81
    ookie
    -0.81
    olls
    -0.80
    awks
    -0.78
    ¯¯
    -0.75
    ucket
    -0.74
    pton
    -0.73
    achine
    -0.72
    POSITIVE LOGITS
     translation
    1.10
     translations
    1.08
     transl
    1.02
     translator
    0.96
    translation
    0.93
     Translation
    0.93
     subtitles
    0.90
     translated
    0.88
    language
    0.83
     translating
    0.81
    Activations Density 0.016%

    No Known Activations