© 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 EvalsExportsAPI 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. 30464
    Prev
    Next
    INDEX
    Explanations

    mentions of key historical political events and figures associated with the Afghan conflict

    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
    391
    +0.12
    0.5%
    637
    +0.12
    0.5%
    520
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.12
    0.06
    725
    +0.12
    0.04
    154
    +0.10
    0.06
    Negative Logits
     Pelicans
    -1.37
     Galile
    -1.20
     Cavs
    -1.10
     Shinra
    -1.08
     Torah
    -1.06
     Hornets
    -1.06
     Catalan
    -1.05
     Galileo
    -1.02
     Raptors
    -0.99
     Cavaliers
    -0.97
    POSITIVE LOGITS
     Taliban
    1.81
     Afghan
    1.78
     Kabul
    1.76
     Afghans
    1.65
     Afghanistan
    1.56
    zai
    1.55
    Pak
    1.43
     Pakistani
    1.42
     Pakistan
    1.39
     Islamabad
    1.39
    Activations Density 2.139%

    No Known Activations