© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26604
    Prev
    Next
    INDEX
    Explanations

    references to milk and its characteristics

    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
    288
    +0.13
    0.6%
    19
    +0.10
    0.4%
    291
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.02
    40
    +0.10
    0.01
    285
    +0.09
    0.01
    Negative Logits
     Manuel
    -0.79
    izons
    -0.71
     Exile
    -0.71
    eering
    -0.69
    nces
    -0.68
    vernment
    -0.67
     resil
    -0.67
    RM
    -0.65
    ISE
    -0.65
    bably
    -0.64
    POSITIVE LOGITS
    weed
    1.27
    maid
    1.18
    waukee
    0.97
     chocolate
    0.94
    mil
    0.94
    fed
    0.91
    fat
    0.91
    cup
    0.88
     yogurt
    0.87
     Milk
    0.86
    Activations Density 0.063%

    No Known Activations