© 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. 11-RES-JB
    11. 20594
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict, disputes, and battles

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to conflicts or disputes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eele
    -0.76
    elin
    -0.71
    orthy
    -0.70
     graduates
    -0.64
     Siber
    -0.63
     recipients
    -0.61
     instructions
    -0.61
    lif
    -0.59
     Estimated
    -0.59
    ayer
    -0.58
    POSITIVE LOGITS
     dispute
    1.63
     feud
    1.59
     quarrel
    1.55
     debate
    1.51
     conflict
    1.48
     disputes
    1.46
     skirm
    1.44
     disagreement
    1.43
     standoff
    1.42
     debates
    1.40
    Activations Density 0.450%

    No Known Activations