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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18919
    Prev
    Next
    INDEX
    Explanations

    texts related to translation and multilingualism

    oai_token-act-pair · gpt-3.5-turbo

    references to languages and linguistic diversity

    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
    seekers
    -0.77
    obyl
    -0.76
    itent
    -0.76
    iversary
    -0.76
    peror
    -0.76
    ividual
    -0.76
     retailers
    -0.76
    emetery
    -0.75
    etheus
    -0.74
     redevelopment
    -0.74
    POSITIVE LOGITS
     Arabic
    1.75
     English
    1.68
     Hindi
    1.56
     Hebrew
    1.54
     Spanish
    1.53
     Mandarin
    1.52
     english
    1.52
     Latin
    1.47
    English
    1.44
     languages
    1.43
    Activations Density 0.305%

    No Known Activations