© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 8409
    Prev
    Next
    INDEX
    Explanations

    words related to luggage or emotional burdens

    oai_token-act-pair · gpt-3.5-turbo

    references to baggage and its metaphorical implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ranch
    -0.70
    yout
    -0.69
     Metatron
    -0.68
     Blaz
    -0.67
    quartered
    -0.67
     Tenn
    -0.66
    atche
    -0.66
     Joker
    -0.66
    knife
    -0.65
    okin
    -0.65
    POSITIVE LOGITS
     baggage
    1.55
     poorer
    1.33
    ILY
    1.29
     DOM
    1.20
     Gerald
    1.12
     richer
    1.12
     confer
    1.01
    uries
    0.93
     Kyr
    0.90
     Vu
    0.88
    Activations Density 0.051%

    No Known Activations