© 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. 26287
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate an effort or attempt to accomplish something

    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
    373
    +0.15
    0.7%
    459
    +0.14
    0.7%
    374
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.15
    0.06
    665
    +0.14
    0.06
    324
    +0.12
    0.04
    Negative Logits
    icka
    -0.74
    nings
    -0.67
    sbm
    -0.64
    pires
    -0.64
    amaz
    -0.64
     thanking
    -0.63
    rica
    -0.62
     sponsoring
    -0.62
    krit
    -0.62
     ordering
    -0.62
    POSITIVE LOGITS
     desperately
    0.80
    å¦
    0.80
     navigate
    0.73
     determine
    0.71
    ãĥĺ
    0.70
    ggles
    0.69
     unsuccessfully
    0.67
    ãĥīãĥ©ãĤ´ãĥ³
    0.67
     decide
    0.66
     define
    0.65
    Activations Density 0.246%

    No Known Activations