© 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. 0-RES-JB
    6. 20071
    Prev
    Next
    INDEX
    Explanations

    phrases related to the news agency "Xinhua"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific Chinese locations or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gear
    -0.67
    arg
    -0.66
     corners
    -0.66
     mod
    -0.65
     ass
    -0.65
    onder
    -0.64
     improv
    -0.63
     intern
    -0.63
     Mod
    -0.62
     bases
    -0.60
    POSITIVE LOGITS
    hua
    4.81
    jiang
    1.59
    hu
    1.44
    hai
    1.35
    hap
    1.33
    ghai
    1.26
     Hua
    1.25
    hao
    1.10
    zhen
    1.10
    yip
    1.09
    Activations Density 0.009%

    No Known Activations