© 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. 5058
    Prev
    Next
    INDEX
    Explanations

    terms related to organized efforts or initiatives, such as campaigns, projects, and reform

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to organized campaigns or initiatives

    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
     fram
    -0.76
     lowly
    -0.74
    ãģĦ
    -0.69
    Frames
    -0.69
    inventoryQuantity
    -0.68
     corners
    -0.63
     slightest
    -0.62
     passages
    -0.61
     sinks
    -0.60
    à¨
    -0.60
    POSITIVE LOGITS
     spearheaded
    1.04
    ĸļ
    0.98
     undertaken
    0.91
    staking
    0.85
     whereby
    0.81
     overseen
    0.79
     dubbed
    0.79
     coordinated
    0.78
    funded
    0.77
     involving
    0.75
    Activations Density 0.266%

    No Known Activations