© 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. 26395
    Prev
    Next
    INDEX
    Explanations

    words expressing necessity or obligation

    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
    141
    +0.10
    0.5%
    326
    +0.10
    0.5%
    188
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.10
    0.06
    139
    +0.10
    0.05
    49
    +0.09
    0.05
    Negative Logits
     ãģ
    -0.62
    ãĥĺãĥ©
    -0.61
     mosqu
    -0.60
    ãĥŃ
    -0.59
     Marlins
    -0.56
     Pug
    -0.55
     Lif
    -0.55
     Slide
    -0.55
     Fiction
    -0.54
     Gw
    -0.54
    POSITIVE LOGITS
    ered
    1.26
    n
    1.25
    ering
    1.20
     surely
    1.16
    ers
    1.10
     therefore
    1.08
    aches
    1.04
     necessarily
    0.96
     nevertheless
    0.94
    afa
    0.92
    Activations Density 0.200%

    No Known Activations