© 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. 14453
    Prev
    Next
    INDEX
    Explanations

    the word "what" followed by other words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    questions or phrases that start with "what."

    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
    enance
    -0.68
    robe
    -0.64
     Emirates
    -0.58
     picking
    -0.57
     largeDownload
    -0.57
     Yards
    -0.56
     Finance
    -0.56
     stride
    -0.55
    xon
    -0.55
    clude
    -0.55
    POSITIVE LOGITS
    soever
    1.09
     happened
    0.98
     happens
    0.95
     transpired
    0.88
    atus
    0.79
     constitutes
    0.79
     kinds
    0.77
     constituted
    0.75
    abouts
    0.74
     else
    0.74
    Activations Density 0.089%

    No Known Activations