© 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. 32718
    Prev
    Next
    INDEX
    Explanations

    instances of the first-person singular pronoun and expressions of personal experience

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    501
    +0.11
    0.5%
    469
    +0.10
    0.4%
    348
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.11
    0.13
    566
    +0.10
    0.11
    519
    +0.10
    0.09
    Negative Logits
    SPONSORED
    -0.77
     Recall
    -0.75
     Virus
    -0.74
    xus
    -0.67
     Convert
    -0.67
     EntityItem
    -0.66
     spurious
    -0.66
    MpServer
    -0.66
    worthiness
    -0.63
     Laden
    -0.61
    POSITIVE LOGITS
     hoping
    1.06
     glad
    0.96
     frustrated
    0.86
     concentrating
    0.81
     disappointed
    0.81
     thankful
    0.80
     trying
    0.80
     accustomed
    0.79
     figuring
    0.78
     enjoying
    0.78
    Activations Density 0.457%

    No Known Activations