© 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 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. 2-RES-JB
    11. 22477
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ron" with varying importance levels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ron"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hower
    -0.81
     sugg
    -0.68
     Annotations
    -0.66
     td
    -0.65
     developing
    -0.63
     clipboard
    -0.62
    ORD
    -0.60
     rhy
    -0.59
    enegger
    -0.59
    displayText
    -0.59
    POSITIVE LOGITS
     Weasley
    0.90
     Paul
    0.90
    Paul
    0.90
    ny
    0.82
     Ron
    0.81
     Swanson
    0.81
    aldo
    0.80
    nen
    0.80
    andom
    0.79
    bie
    0.78
    Activations Density 0.005%

    No Known Activations