© 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. 4-RES-JB
    11. 14319
    Prev
    Next
    INDEX
    Explanations

    references to the word "nik" in a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sputnik" and variations of the word "Nik."

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

    No Comments

    Negative Logits
    ASED
    -0.70
    ULTS
    -0.68
    20439
    -0.67
     GST
    -0.66
    benefit
    -0.65
    ,,,,,,,,
    -0.65
     setbacks
    -0.62
    FH
    -0.60
     welf
    -0.60
    Rare
    -0.59
    POSITIVE LOGITS
    nik
    1.11
    lar
    1.04
    kel
    1.03
    ken
    0.95
    kie
    0.93
    ova
    0.91
    ety
    0.89
    las
    0.87
    achu
    0.86
    opol
    0.85
    Activations Density 0.009%

    No Known Activations