© 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. 30140
    Prev
    Next
    INDEX
    Explanations

    references to political and military conflict, particularly involving rebel groups and governmental actions

    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
    314
    +0.18
    0.8%
    574
    +0.10
    0.5%
    242
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.18
    0.06
    314
    +0.10
    0.01
    102
    +0.09
    0.06
    Negative Logits
     veins
    -0.79
     Beam
    -0.71
     darts
    -0.70
     equival
    -0.69
     similarity
    -0.69
     attractiveness
    -0.68
     immersion
    -0.68
     heights
    -0.67
     imitation
    -0.67
     clocks
    -0.66
    POSITIVE LOGITS
    dominated
    1.47
    appointed
    1.46
    controlled
    1.40
    backed
    1.37
    held
    1.33
    aligned
    1.30
    affiliated
    1.29
    linked
    1.28
    run
    1.28
    led
    1.26
    Activations Density 0.279%

    No Known Activations