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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 22673
    Prev
    Next
    INDEX
    Explanations

    phrases related to intense competition or rivalry between individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to rivalry and competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tarian
    -0.70
    annis
    -0.69
    asel
    -0.69
    erd
    -0.67
    assy
    -0.67
    aer
    -0.66
    storage
    -0.66
    lying
    -0.66
    cise
    -0.65
    arers
    -0.65
    POSITIVE LOGITS
     rivalry
    1.27
     rival
    0.91
    hips
    0.86
     rivals
    0.83
     Royale
    0.81
    halla
    0.77
    yip
    0.76
     feud
    0.75
    riors
    0.74
    SHIP
    0.71
    Activations Density 0.010%

    No Known Activations