© 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. 31288
    Prev
    Next
    INDEX
    Explanations

    references to countries and their political interactions, especially concerning the U.S. government and foreign policy

    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
    700
    +0.10
    0.5%
    331
    +0.10
    0.5%
    362
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.11
    732
    +0.10
    0.04
    752
    +0.10
    0.09
    Negative Logits
    estamp
    -0.79
    swer
    -0.73
    agos
    -0.66
     populace
    -0.65
    porter
    -0.65
     proletariat
    -0.64
    cients
    -0.64
    »Ĵ
    -0.64
     anybody
    -0.63
    ouf
    -0.62
    POSITIVE LOGITS
     efforts
    0.96
     concerns
    0.91
     objections
    0.87
     teachings
    0.83
     suspicions
    0.82
     practices
    0.81
     fears
    0.81
     speculation
    0.81
     plans
    0.80
     deliberations
    0.79
    Activations Density 1.189%

    No Known Activations