© 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. 26495
    Prev
    Next
    INDEX
    Explanations

    instances of notable performances and achievements in entertainment and charity

    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
    324
    +0.13
    0.6%
    700
    +0.12
    0.5%
    626
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.23
    324
    +0.12
    0.15
    693
    +0.10
    0.16
    Negative Logits
     depended
    -0.81
     transpired
    -0.74
     existed
    -0.72
     mattered
    -0.67
    they
    -0.67
    soever
    -0.66
     Administ
    -0.65
     decreased
    -0.64
     differed
    -0.64
     nor
    -0.62
    POSITIVE LOGITS
     alongside
    1.03
     atop
    1.02
     onstage
    0.93
     himself
    0.92
     Himself
    0.85
     backstage
    0.84
     wielding
    0.83
     amidst
    0.81
     posing
    0.81
     proclaiming
    0.79
    Activations Density 4.945%

    No Known Activations