© 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. 16129
    Prev
    Next
    INDEX
    Explanations

    words related to organizations or teams, particularly focusing on a specific entity named "Liquid" and another called "Dignitas"

    oai_token-act-pair · gpt-3.5-turbo

    references to the esports organization Liquid and mentions of dignity-related terms

    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
    olkien
    -0.82
     amuse
    -0.77
    ueller
    -0.72
    oulos
    -0.69
    EngineDebug
    -0.68
     Manson
    -0.68
    Tes
    -0.67
    ishly
    -0.66
     fries
    -0.66
     mol
    -0.66
    POSITIVE LOGITS
     Dign
    0.96
    ity
    0.90
    itas
    0.89
    iant
    0.78
    itary
    0.78
    iciary
    0.78
    iolet
    0.75
     Numbers
    0.74
    taker
    0.74
    essee
    0.74
    Activations Density 0.019%

    No Known Activations