© 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. 8794
    Prev
    Next
    INDEX
    Explanations

    phrases encouraging user engagement and interaction

    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
    373
    +0.15
    0.7%
    394
    +0.10
    0.4%
    78
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.15
    -0.04
    32
    +0.10
    0.06
    182
    +0.09
    0.05
    Negative Logits
     terminology
    -0.74
     elig
    -0.70
     umb
    -0.68
     intermedi
    -0.67
     supervision
    -0.67
     timet
    -0.65
     mund
    -0.65
     confidentiality
    -0.65
    Cooldown
    -0.65
     propri
    -0.64
    POSITIVE LOGITS
    iked
    0.87
    Ü
    0.78
    itiveness
    0.74
    ãĥ©ãĥ³
    0.73
    vertisement
    0.73
    pling
    0.73
     Favorite
    0.72
     disliked
    0.70
    icked
    0.68
    share
    0.68
    Activations Density 0.823%

    No Known Activations