© 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. 6-RES-JB
    11. 17344
    Prev
    Next
    INDEX
    Explanations

    competitive words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "competitive."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AMI
    -0.78
    gur
    -0.77
    stones
    -0.76
    hung
    -0.73
    DonaldTrump
    -0.72
    ################
    -0.71
    qt
    -0.71
    ANG
    -0.69
    FORE
    -0.66
    uras
    -0.66
    POSITIVE LOGITS
     juices
    0.93
     advantages
    0.93
    ly
    0.92
     minded
    0.92
     advantage
    0.87
     Advantage
    0.86
     pressures
    0.83
     multiplayer
    0.83
     viability
    0.80
     disadvantage
    0.79
    Activations Density 0.018%

    No Known Activations