© 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. 8736
    Prev
    Next
    INDEX
    Explanations

    phrases related to partnerships and collaborations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    193
    +0.10
    0.5%
    518
    +0.10
    0.5%
    322
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.06
    608
    +0.10
    0.07
    479
    +0.09
    0.03
    Negative Logits
    rencies
    -0.80
    xual
    -0.77
    clips
    -0.73
    aucuses
    -0.73
    osaurs
    -0.72
    imental
    -0.70
     pregnancies
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
    alone
    -0.68
    SpaceEngineers
    -0.67
    POSITIVE LOGITS
    senal
    0.74
     Hoy
    0.74
     Rah
    0.68
     Hond
    0.68
     Panasonic
    0.68
     Oprah
    0.67
     Pittsburgh
    0.66
     partner
    0.66
     Indy
    0.66
     Kinnikuman
    0.65
    Activations Density 0.519%

    No Known Activations