© 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. 7-RES-JB
    11. 13913
    Prev
    Next
    INDEX
    Explanations

    words related to the Jewish language Yiddish

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the Yiddish language and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rency
    -0.81
    enment
    -0.71
    fitting
    -0.67
    ãĥ¼ãĥĨ
    -0.65
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
    eele
    -0.63
    rawdownloadcloneembedreportprint
    -0.59
    ctive
    -0.59
    ength
    -0.59
    ãĥĥãĥĪ
    -0.58
    POSITIVE LOGITS
    oslav
    0.78
    abytes
    0.77
    akov
    0.75
    abyte
    0.70
    gm
    0.65
    gi
    0.65
    know
    0.63
    iga
    0.63
    arkin
    0.63
    aston
    0.63
    Activations Density 0.054%

    No Known Activations