© 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. 6-RES-JB
    6. 11894
    Prev
    Next
    INDEX
    Explanations

    words related to language or location, with a focus on specific languages or countries

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of certain non-English or special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyde
    -0.86
    aged
    -0.71
    agall
    -0.71
    ipolar
    -0.68
    ammy
    -0.67
    ucket
    -0.66
    abase
    -0.65
    ahar
    -0.65
    aging
    -0.65
    ngth
    -0.61
    POSITIVE LOGITS
    ãĤī
    1.00
    ת
    0.96
    ×Ļ×
    0.95
    IJ
    0.93
    κ
    0.92
    ׾
    0.90
    ä
    0.85
    ×ķ
    0.85
    ä¸ī
    0.85
    æĢ
    0.80
    Activations Density 0.033%

    No Known Activations