© 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. 26227
    Prev
    Next
    INDEX
    Explanations

    numerical values or identifiers related to technology or programming

    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
    675
    +0.10
    0.5%
    425
    +0.10
    0.5%
    520
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.10
    0.02
    640
    +0.10
    0.20
    375
    +0.10
    0.04
    Negative Logits
    ertodd
    -0.81
    Ĥª
    -0.71
     Hayward
    -0.71
    =-=-
    -0.68
    rera
    -0.66
    ļ
    -0.66
    astered
    -0.66
    baugh
    -0.65
    alez
    -0.65
    isner
    -0.65
    POSITIVE LOGITS
     N
    2.33
    N
    2.06
     n
    1.74
    Ns
    1.64
    n
    1.47
     NIC
    1.42
    NN
    1.41
     Nu
    1.39
    NH
    1.37
     NE
    1.36
    Activations Density 8.797%

    No Known Activations