© 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. 3981
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Nas"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term 'Nas' and its variations in the context of health or personal experiences

    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
    éģ
    -0.65
    PsyNetMessage
    -0.65
    enance
    -0.64
    é»Ĵ
    -0.63
    å§
    -0.62
    ãĥį
    -0.62
    OTT
    -0.62
    ffee
    -0.62
     damned
    -0.61
     Glory
    -0.59
    POSITIVE LOGITS
    daq
    1.90
     Nas
    1.17
    DAQ
    1.11
    rils
    0.94
    emonic
    0.92
     nas
    0.91
     charact
    0.87
    apon
    0.84
    emic
    0.84
    ilon
    0.82
    Activations Density 0.004%

    No Known Activations