© 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. 10-RES_POST_32K-OAI
    11. 30519
    Prev
    Next
    INDEX
    Explanations

    elements of conflict and confrontation

    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
    346
    +0.17
    0.7%
    337
    +0.12
    0.5%
    368
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.17
    0.12
    43
    +0.12
    0.11
    546
    +0.12
    0.09
    Negative Logits
     nor
    -0.72
     anytime
    -0.69
     dearly
    -0.69
    unless
    -0.67
     Indeed
    -0.65
    ardless
    -0.65
    Indeed
    -0.63
     Absent
    -0.62
    enance
    -0.61
     appendix
    -0.61
    POSITIVE LOGITS
    then
    1.04
     intending
    0.98
    where
    0.84
     then
    0.82
     asking
    0.79
     causing
    0.77
     requesting
    0.76
     knocking
    0.76
     hoping
    0.74
     initiating
    0.74
    Activations Density 1.230%

    No Known Activations