© 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. 3-RES-JB
    11. 23046
    Prev
    Next
    INDEX
    Explanations

    names or words related to patriotism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to patriotism and national pride

    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
     Sands
    -0.79
    cloth
    -0.63
    Motion
    -0.63
     Thomson
    -0.61
    edited
    -0.61
    water
    -0.61
    words
    -0.61
     Hamm
    -0.60
     Corrections
    -0.60
    ward
    -0.60
    POSITIVE LOGITS
    umerable
    0.85
     enumer
    0.81
     patriotic
    0.80
    mble
    0.75
    anooga
    0.74
     patriotism
    0.73
    ighty
    0.71
    owers
    0.70
    ethyst
    0.70
    ortunate
    0.69
    Activations Density 0.024%

    No Known Activations