© 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. 10-RES-JB
    11. 2291
    Prev
    Next
    INDEX
    Explanations

    words related to languages or translations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of languages and subtitles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.93
    urion
    -0.86
    olicy
    -0.84
    gaard
    -0.81
    hardt
    -0.76
    anmar
    -0.75
    seeking
    -0.75
    ilitarian
    -0.74
    achine
    -0.74
    ividual
    -0.72
    POSITIVE LOGITS
     translation
    1.47
     pronunciation
    1.38
     subtitles
    1.36
     translations
    1.33
     language
    1.30
     diction
    1.24
     dictionary
    1.22
     spelling
    1.18
    language
    1.14
     speakers
    1.14
    Activations Density 0.078%

    No Known Activations