© 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. 6197
    Prev
    Next
    INDEX
    Explanations

    references to studies and research involving couples, particularly in the context of health or personal relationships

    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
    626
    +0.12
    0.6%
    74
    +0.12
    0.5%
    436
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    697
    +0.12
    0.06
    139
    +0.12
    0.08
    718
    +0.11
    0.11
    Negative Logits
    Still
    -0.73
    ocaust
    -0.64
     detract
    -0.64
     Still
    -0.63
     resorted
    -0.62
    Weak
    -0.61
    VERTISEMENT
    -0.59
    Sometimes
    -0.58
    othe
    -0.57
     Lastly
    -0.57
    POSITIVE LOGITS
     consisted
    0.94
     ostensibly
    0.81
     promptly
    0.75
     greeted
    0.74
     comprised
    0.73
     hailed
    0.73
     astonished
    0.72
     duly
    0.72
     consists
    0.71
     immediately
    0.70
    Activations Density 3.918%

    No Known Activations