© 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. 10348
    Prev
    Next
    INDEX
    Explanations

    the specific word "Xenia"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Xen" and related names or concepts

    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
    姫
    -0.88
    ãĢij
    -0.82
    ÑĢ
    -0.81
    м
    -0.79
    л
    -0.79
    enegger
    -0.76
    س
    -0.73
    é¾įå¥ij士
    -0.73
    glers
    -0.73
    в
    -0.73
    POSITIVE LOGITS
    peria
    1.08
    ophon
    1.03
    osaurs
    0.97
    ocry
    0.96
     Xen
    0.95
    anth
    0.94
    ython
    0.93
    agos
    0.91
    ozo
    0.89
    posium
    0.87
    Activations Density 0.012%

    No Known Activations