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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 2343
    Prev
    Next
    INDEX
    Explanations

    references to militia groups and related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of militia groups

    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
    âĸ¬
    -0.73
    paren
    -0.69
    mone
    -0.69
     Wheat
    -0.68
    ectar
    -0.67
    èª
    -0.66
    eating
    -0.66
     Prediction
    -0.64
    val
    -0.64
    Oracle
    -0.63
    POSITIVE LOGITS
     militias
    1.12
     militia
    1.09
     commanders
    0.92
     brig
    0.89
     commander
    0.86
     members
    0.84
     patrols
    0.83
    ilitary
    0.83
     paramilitary
    0.80
     councill
    0.80
    Activations Density 0.016%

    No Known Activations