Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3594
    Prev
    Next
    INDEX
    Explanations

    language related to patriotism and the Patriot Act

    oai_token-act-pair · gpt-3.5-turbo

    words associated with patriotism and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orne
    -0.70
    er
    -0.69
    Tool
    -0.68
    worm
    -0.68
    caster
    -0.68
    err
    -0.67
     accelerator
    -0.67
    bench
    -0.65
    ussed
    -0.65
    way
    -0.64
    POSITIVE LOGITS
    riots
    0.92
     patriotic
    0.89
     patri
    0.85
     patriot
    0.85
     Patriot
    0.84
    éĹĺ
    0.78
    riot
    0.76
    sburg
    0.75
    dinand
    0.75
     patriotism
    0.74
    Activations Density 0.032%

    No Known Activations