© 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. 31603
    Prev
    Next
    INDEX
    Explanations

    expressions of welcoming or greeting sentiments

    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
    222
    +0.11
    0.5%
    759
    +0.11
    0.5%
    594
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    222
    +0.11
    0.02
    144
    +0.11
    0.01
    339
    +0.11
    0.02
    Negative Logits
    tein
    -0.93
    arcity
    -0.90
    uyomi
    -0.78
    olls
    -0.76
    aunder
    -0.76
    Downloadha
    -0.75
    negie
    -0.69
    eki
    -0.68
    iple
    -0.67
    oled
    -0.67
    POSITIVE LOGITS
     newcomers
    1.09
     aboard
    1.05
     guests
    0.97
     arrivals
    0.95
     visitors
    0.93
     additions
    0.91
     arrival
    0.89
     back
    0.88
     visitor
    0.85
     home
    0.85
    Activations Density 0.178%

    No Known Activations