© 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. 23051
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with "Ja"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Ja" in various contexts

    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
    âĶģ
    -0.95
    ä¹ĭ
    -0.79
    姫
    -0.77
    Interstitial
    -0.76
    istration
    -0.73
    liness
    -0.73
     Cosponsors
    -0.72
    ãģķ
    -0.72
     Geographic
    -0.72
    天
    -0.71
    POSITIVE LOGITS
     Ja
    0.93
    ques
    0.90
    quet
    0.89
    ¶ħ
    0.87
    ibaba
    0.83
    Ja
    0.80
    ataka
    0.79
     indu
    0.79
    ignt
    0.78
    undai
    0.78
    Activations Density 0.004%

    No Known Activations