© 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. 26243
    Prev
    Next
    INDEX
    Explanations

    punctuations, particularly periods and exclamation marks

    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
    373
    +0.15
    0.7%
    267
    +0.13
    0.6%
    687
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.15
    0.22
    145
    +0.13
    0.15
    622
    +0.12
    0.12
    Negative Logits
     interpre
    -0.74
    verning
    -0.73
    acteria
    -0.70
    ewitness
    -0.70
    untary
    -0.69
    Therefore
    -0.69
    arcer
    -0.67
    Individual
    -0.67
    instein
    -0.66
    Supporters
    -0.66
    POSITIVE LOGITS
    Yep
    1.37
     Hmm
    1.35
     Yep
    1.35
     Damn
    1.26
    Seriously
    1.25
     eh
    1.25
     Nope
    1.25
    HAHAHAHA
    1.24
    Damn
    1.23
     Oops
    1.21
    Activations Density 1.732%

    No Known Activations