© 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. 8-RES-JB
    11. 21757
    Prev
    Next
    INDEX
    Explanations

    phrases related to packing, moving, or organizing items

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of packing or moving belongings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onal
    -0.79
    ²¾
    -0.77
     Television
    -0.74
    xual
    -0.70
    iliate
    -0.70
    ĨĴ
    -0.68
    Ħ¢
    -0.66
     attribution
    -0.65
     Morse
    -0.64
    ĸļ
    -0.63
    POSITIVE LOGITS
     bags
    1.23
     suitcase
    1.16
     belongings
    1.14
     crates
    1.12
     luggage
    1.05
     shelves
    1.01
    ainers
    1.00
    bags
    1.00
     cargo
    0.96
     groceries
    0.93
    Activations Density 0.240%

    No Known Activations