© 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. 8804
    Prev
    Next
    INDEX
    Explanations

    titles and names of video games

    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
    719
    +0.10
    0.5%
    470
    +0.09
    0.4%
    136
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.06
    476
    +0.09
    0.03
    530
    +0.09
    0.04
    Negative Logits
     recl
    -0.73
     pharmacies
    -0.72
    ussian
    -0.70
     horizont
    -0.70
     allot
    -0.65
     squats
    -0.65
     understatement
    -0.64
    kell
    -0.64
     aph
    -0.64
    alach
    -0.63
    POSITIVE LOGITS
     Edition
    0.85
    士
    0.81
     Revenge
    0.77
     Series
    0.77
     Legendary
    0.74
    ãĥ©ãĥ³
    0.73
     Vengeance
    0.73
     Deluxe
    0.72
     Definitive
    0.72
     Dimensions
    0.70
    Activations Density 0.459%

    No Known Activations