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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    6. 6973
    Prev
    Next
    INDEX
    Explanations

    Japanese names

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to Japanese culture and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brance
    -0.83
    med
    -0.70
     Lyme
    -0.69
     skelet
    -0.68
    eworld
    -0.64
    tc
    -0.64
    mes
    -0.63
     Doe
    -0.62
     Orbit
    -0.62
     Gree
    -0.61
    POSITIVE LOGITS
    etsu
    1.21
    atsu
    0.99
    hiro
    0.98
    imura
    0.96
    pport
    0.96
    ushima
    0.90
    arya
    0.88
    jin
    0.88
    ichi
    0.85
    itsu
    0.84
    Activations Density 0.016%

    No Known Activations