© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 7097
    Prev
    Next
    INDEX
    Explanations

    references to "Cirque du Soleil" and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    479
    +0.11
    0.5%
    309
    +0.10
    0.5%
    192
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.11
    0.09
    659
    +0.10
    0.08
    232
    +0.10
    0.09
    Negative Logits
    inar
    -1.05
    urer
    -0.99
    riter
    -0.99
    bage
    -0.97
    keyes
    -0.96
    jri
    -0.96
    rals
    -0.96
    orer
    -0.95
    issues
    -0.95
    uler
    -0.94
    POSITIVE LOGITS
     Oriental
    0.79
     Mu
    0.75
     Plaza
    0.75
     Alpha
    0.75
     Univers
    0.75
     Grande
    0.74
     Sinai
    0.73
     Hua
    0.72
     Bung
    0.71
     Gamma
    0.71
    Activations Density 0.848%

    No Known Activations