© 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. 8-RES_POST_32K-OAI
    11. 9037
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future events or expectations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.12
    0.5%
    490
    +0.09
    0.4%
    101
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    106
    +0.12
    0.03
    38
    +0.09
    0.03
    101
    +0.09
    0.03
    Negative Logits
    pection
    -0.57
    cius
    -0.56
    rehens
    -0.53
     Except
    -0.53
     unthinkable
    -0.53
    ruct
    -0.52
    cv
    -0.52
    how
    -0.52
     Imagine
    -0.52
    tein
    -0.52
    POSITIVE LOGITS
    Ĥİ
    0.80
     soon
    0.75
    soon
    0.67
     Parenthood
    0.64
     Beir
    0.61
    itialized
    0.60
     later
    0.59
     shortly
    0.58
    Į
    0.58
    ãĥŀ
    0.58
    Activations Density 0.092%

    No Known Activations