© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 553
    Prev
    Next
    INDEX
    Explanations

    questions beginning with the word "What" in a sentence structure that suggests inquiry about a specific topic

    oai_token-act-pair · gpt-3.5-turbo

    interrogative words or phrases, specifically questions

    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
    tin
    -0.73
    loading
    -0.71
    general
    -0.67
    fm
    -0.67
    boat
    -0.66
    amed
    -0.66
    mage
    -0.66
    boats
    -0.65
    Interstitial
    -0.64
    tur
    -0.64
    POSITIVE LOGITS
     Lies
    0.98
     Makes
    0.91
     Definitions
    0.91
     Facts
    0.90
    soever
    0.87
     Links
    0.81
     Changes
    0.80
     Documents
    0.78
     Votes
    0.77
     Causes
    0.77
    Activations Density 0.093%

    No Known Activations