© 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. 6-RES-JB
    11. 14462
    Prev
    Next
    INDEX
    Explanations

    the word "anda" occurring in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "anda" specifically in various contexts

    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
    sed
    -0.97
    bard
    -0.86
    paio
    -0.78
    lav
    -0.78
    icka
    -0.77
    ensible
    -0.77
    alcohol
    -0.77
    nesota
    -0.76
    dn
    -0.75
    cffff
    -0.73
    POSITIVE LOGITS
    emonium
    1.21
     Devi
    0.90
     Haram
    0.84
    isance
    0.79
    Äĩ
    0.78
    ibo
    0.77
    emon
    0.74
    uthor
    0.73
     Saras
    0.69
     Chatt
    0.69
    Activations Density 0.028%

    No Known Activations