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. 4-RES-JB
    6. 23833
    Prev
    Next
    INDEX
    Explanations

    mentions of language or regions, specifically Hindi and Tamil

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific South Asian languages, particularly Hindi and Tamil

    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
    apego
    -0.91
    rex
    -0.90
    hardt
    -0.89
    paio
    -0.88
    egg
    -0.88
    affles
    -0.82
    ertodd
    -0.81
    inery
    -0.79
    oit
    -0.79
    idem
    -0.78
    POSITIVE LOGITS
     Nadu
    1.36
     chanting
    0.78
     Tamil
    0.78
     voices
    0.77
     learners
    0.77
     chant
    0.74
     subtitles
    0.70
     awakening
    0.69
     opera
    0.69
     Revival
    0.68
    Activations Density 0.017%

    No Known Activations