© 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. 19021
    Prev
    Next
    INDEX
    Explanations

    words related to competition or conflict, especially in the context of rivals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of competition or opponents

    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
     Keys
    -0.66
     ok
    -0.64
    herty
    -0.63
    acs
    -0.62
    wm
    -0.60
    archy
    -0.60
    ctx
    -0.60
    ork
    -0.59
     inserts
    -0.59
    ZE
    -0.59
    POSITIVE LOGITS
     rival
    3.92
     rivals
    2.99
     competitor
    2.08
    rival
    1.85
     competitors
    1.78
     rivalry
    1.61
     challenger
    1.57
     competing
    1.52
     foe
    1.47
     challengers
    1.41
    Activations Density 0.006%

    No Known Activations