© 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. 9044
    Prev
    Next
    INDEX
    Explanations

    structured information regarding systems or categories

    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
    143
    +0.10
    0.4%
    640
    +0.09
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.08
    6
    +0.09
    0.07
    308
    +0.09
    0.04
    Negative Logits
     moreover
    -0.83
     conclud
    -0.83
     furthermore
    -0.82
     subsequently
    -0.76
    ilogy
    -0.75
    iasco
    -0.74
    .}
    -0.74
    conservancy
    -0.74
     proble
    -0.72
    sers
    -0.72
    POSITIVE LOGITS
    Medium
    0.91
     Medium
    0.88
     Mild
    0.84
     Moderate
    0.80
    Avg
    0.80
    âĺħâĺħ
    0.77
     None
    0.75
     Normal
    0.74
     Intermediate
    0.73
    ãĥ©ãĥ³
    0.72
    Activations Density 0.569%

    No Known Activations