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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22576
    Prev
    Next
    INDEX
    Explanations

    would be words related to competition or competitiveness

    oai_token-act-pair · gpt-3.5-turbo

    the term "compete" in various contexts related to competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    attribute
    -0.72
    ward
    -0.69
    haul
    -0.66
    anger
    -0.63
    sight
    -0.62
    hak
    -0.62
    Anth
    -0.61
    thus
    -0.61
    hod
    -0.60
    fab
    -0.58
    POSITIVE LOGITS
     competing
    0.86
     competitions
    0.82
    ivity
    0.82
    estyles
    0.81
     compete
    0.81
    halla
    0.78
    competitive
    0.77
     competed
    0.77
    daq
    0.76
     competitors
    0.75
    Activations Density 0.008%

    No Known Activations