© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31969
    Prev
    Next
    INDEX
    Explanations

    the presence of actions and conditions related to governmental and organizational processes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    756
    +0.18
    0.9%
    86
    +0.15
    0.7%
    665
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.18
    0.18
    49
    +0.15
    0.17
    139
    +0.14
    0.16
    Negative Logits
     Dying
    -0.76
    Die
    -0.75
    hot
    -0.74
     cameo
    -0.70
     weeping
    -0.70
    die
    -0.69
     Cry
    -0.69
     Tears
    -0.69
     Rage
    -0.68
     confessed
    -0.67
    POSITIVE LOGITS
     incentiv
    1.37
     incent
    1.21
     mandate
    1.13
     legisl
    1.10
     mandates
    0.99
     policymakers
    0.97
     discourage
    0.96
     mand
    0.96
     privat
    0.96
     decentral
    0.95
    Activations Density 1.106%

    No Known Activations