© 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. 10-RES-JB
    11. 2851
    Prev
    Next
    INDEX
    Explanations

    words related to conflicts, disagreements, and disputes

    oai_token-act-pair · gpt-3.5-turbo

    words related to conflicts and disputes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elin
    -0.72
    eele
    -0.71
    akeru
    -0.67
    vale
    -0.66
     footprints
    -0.66
     stocking
    -0.66
    erton
    -0.66
    iaries
    -0.62
     Atmospheric
    -0.62
    ECD
    -0.59
    POSITIVE LOGITS
     between
    1.48
    between
    1.21
     ensued
    1.14
     raged
    1.13
     waged
    1.13
     raging
    1.12
     erupted
    1.05
     unresolved
    0.99
     erupt
    0.99
     brewing
    0.98
    Activations Density 0.242%

    No Known Activations