© 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. 1-RES-JB
    6. 11463
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of specific names, particularly "Xin," "Jade," and "Ming."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburgh
    -1.09
    perature
    -0.86
    Ö¼
    -0.85
    awaru
    -0.77
    inctions
    -0.74
    phis
    -0.71
    ersion
    -0.70
    elsen
    -0.70
    ramid
    -0.69
    sky
    -0.69
    POSITIVE LOGITS
     Xin
    1.36
    jiang
    1.15
    hua
    0.99
     Gong
    0.93
     Fang
    0.89
    jin
    0.86
     Xie
    0.85
     Jinping
    0.83
    leigh
    0.82
     Hua
    0.81
    Activations Density 0.009%

    No Known Activations