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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29475
    Prev
    Next
    INDEX
    Explanations

    terms related to social and political concepts

    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
    316
    +0.12
    0.6%
    373
    +0.12
    0.6%
    469
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.12
    0.07
    284
    +0.12
    0.05
    316
    +0.10
    0.04
    Negative Logits
    idate
    -1.04
    orously
    -1.04
    uder
    -0.93
    ese
    -0.92
    idation
    -0.90
    iny
    -0.90
    using
    -0.89
    ivia
    -0.88
    ancing
    -0.88
    ooting
    -0.88
    POSITIVE LOGITS
     et
    0.81
     qui
    0.81
     dur
    0.80
     ont
    0.78
     ;
    0.78
     recomm
    0.77
     partic
    0.75
     sr
    0.74
     liv
    0.70
     nil
    0.68
    Activations Density 0.303%

    No Known Activations