© 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. 6007
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical quantities and measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to environmental resources and sustainability

    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
    rentices
    -0.77
    yrinth
    -0.76
     Architects
    -0.75
    ²¾
    -0.73
    yssey
    -0.70
    agonists
    -0.69
    Trigger
    -0.68
    itect
    -0.68
    ancies
    -0.67
    ikers
    -0.67
    POSITIVE LOGITS
     excess
    1.31
     leftover
    1.09
     residual
    1.05
     stuff
    0.99
    stuff
    0.99
     surplus
    0.96
     portion
    0.93
     raw
    0.92
     bulk
    0.91
     amounts
    0.90
    Activations Density 0.727%

    No Known Activations