© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 13620
    Prev
    Next
    INDEX
    Explanations

    locations, particularly focusing on cities and countries

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the names "Shen" and "Chern."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.76
    dress
    -0.74
     gearing
    -0.70
    adjust
    -0.68
    give
    -0.67
    enforcement
    -0.66
    Reference
    -0.66
    exempt
    -0.65
    unct
    -0.65
    fitting
    -0.64
    POSITIVE LOGITS
     Shen
    1.30
     Jing
    1.03
    zhen
    1.01
     Xiang
    0.96
    hou
    0.95
    zhou
    0.94
    ando
    0.94
    nai
    0.94
    arest
    0.93
    achu
    0.84
    Activations Density 0.004%

    No Known Activations