© 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. 9-RES-JB
    11. 18273
    Prev
    Next
    INDEX
    Explanations

    proper names or terms that include a single uppercase letter followed by zero or more lowercase letters

    oai_token-act-pair · gpt-3.5-turbo

    specific brand names or products, particularly in the context of entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibling
    -0.71
    ovych
    -0.65
    CLASS
    -0.62
    idays
    -0.60
    ¯
    -0.59
    sung
    -0.59
     entitle
    -0.59
     toget
    -0.57
    gging
    -0.57
    learn
    -0.56
    POSITIVE LOGITS
    ulhu
    1.22
    ornia
    1.01
    xus
    0.89
    ortium
    0.86
    ioxide
    0.85
    aign
    0.82
    oglu
    0.78
    igham
    0.76
     Unch
    0.72
    arette
    0.71
    Activations Density 0.584%

    No Known Activations