© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 10032
    Prev
    Next
    INDEX
    Explanations

    names of Japanese individuals and entities

    oai_token-act-pair · gpt-3.5-turbo

    names of Japanese creators and their works related to video games and anime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulence
    -0.83
    undy
    -0.78
    Colorado
    -0.78
    tering
    -0.77
    matically
    -0.75
    sheet
    -0.74
    paren
    -0.71
    rals
    -0.71
    sheets
    -0.70
    eanor
    -0.69
    POSITIVE LOGITS
     Yosh
    1.30
    ichi
    1.28
     Tsuk
    1.27
     Mats
    1.24
     Tanaka
    1.23
    jin
    1.21
     Hiro
    1.20
    ji
    1.17
    ya
    1.17
    oka
    1.15
    Activations Density 0.168%

    No Known Activations