© 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. 26453
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of "even" in various contexts and its significance

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    671
    +0.12
    0.5%
    498
    +0.10
    0.4%
    171
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.07
    608
    +0.10
    0.06
    616
    +0.09
    0.04
    Negative Logits
    ĺħ
    -0.74
    folios
    -0.70
    Feed
    -0.69
    terday
    -0.68
    along
    -0.67
    =-=-=-=-
    -0.66
    ahime
    -0.64
    etc
    -0.64
    pour
    -0.63
    aliation
    -0.63
    POSITIVE LOGITS
     curs
    1.19
     modest
    1.02
     smallest
    0.99
     rudimentary
    0.98
     lowly
    0.98
     innocuous
    0.94
     slightest
    0.92
     casual
    0.87
     novice
    0.87
     mundane
    0.85
    Activations Density 0.576%

    No Known Activations