© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 27109
    Prev
    Next
    INDEX
    Explanations

    references to military units, actions, and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    172
    +0.11
    0.5%
    100
    +0.10
    0.4%
    631
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    742
    +0.11
    0.08
    100
    +0.10
    0.08
    154
    +0.09
    0.12
    Negative Logits
    thereum
    -0.87
     Yelp
    -0.84
    Bitcoin
    -0.79
    Consumer
    -0.78
     Ethereum
    -0.76
     Oprah
    -0.76
     Rowling
    -0.75
    Meta
    -0.75
    conom
    -0.74
     Blockchain
    -0.72
    POSITIVE LOGITS
     infantry
    1.80
     battalion
    1.75
     Infantry
    1.74
     platoon
    1.61
     troops
    1.58
     artillery
    1.58
     commanders
    1.57
     garrison
    1.51
     Regiment
    1.51
     troop
    1.51
    Activations Density 10.771%

    No Known Activations