© 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. 10-RES_POST_32K-OAI
    11. 32670
    Prev
    Next
    INDEX
    Explanations

    occurrences of terms related to packaging or containers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    +0.16
    0.7%
    514
    +0.11
    0.5%
    39
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    514
    +0.16
    0.01
    345
    +0.11
    0.01
    221
    +0.09
    0.00
    Negative Logits
    markets
    -0.70
     agre
    -0.69
     streng
    -0.68
     arrang
    -0.66
    uten
    -0.64
    ollah
    -0.62
     rul
    -0.61
    annis
    -0.61
     Markets
    -0.61
     heartbeat
    -0.60
    POSITIVE LOGITS
    !/
    0.97
    ridor
    0.70
    enge
    0.68
    urbed
    0.67
    ->
    0.67
    atari
    0.66
     *
    0.66
    anism
    0.65
    quished
    0.64
    nam
    0.62
    Activations Density 0.035%

    No Known Activations