© 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. 1-RES-JB
    11. 12925
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and phrases related to East Asian locations

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols representing non-Latin scripts or unique encoding characters

    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
    icka
    -0.87
    ftime
    -0.82
     assemb
    -0.78
    eele
    -0.75
    espie
    -0.72
    linger
    -0.72
    anol
    -0.70
    odic
    -0.69
    eson
    -0.68
    sterdam
    -0.67
    POSITIVE LOGITS
    æ
    1.43
    é
    1.41
    æĹ
    1.40
    ¥
    1.38
    åħ
    1.38
    å
    1.36
    äº
    1.36
    è
    1.36
    ³
    1.34
    ç
    1.33
    Activations Density 0.010%

    No Known Activations