© 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. 9-RES-JB
    11. 11667
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to dramatic or intense actions and exchanges

    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
    MAT
    -0.94
    mat
    -0.93
     Nat
    -0.79
    model
    -0.78
     Monster
    -0.76
     Maxim
    -0.72
    Monster
    -0.71
    amer
    -0.71
    91
    -0.71
    Nat
    -0.70
    POSITIVE LOGITS
    oglu
    0.96
    ÄŁ
    0.92
     ^
    0.87
    Fle
    0.85
     Bleach
    0.84
     Kro
    0.81
    ^{
    0.81
     Fle
    0.78
    د
    0.76
    inventoryQuantity
    0.76
    Activations Density 0.581%

    No Known Activations