© 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. 31697
    Prev
    Next
    INDEX
    Explanations

    emotional responses and reactions to events

    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
    105
    +0.12
    0.5%
    378
    +0.09
    0.4%
    296
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.12
    0.12
    718
    +0.09
    0.10
    762
    +0.09
    0.10
    Negative Logits
    itism
    -0.62
     exceptions
    -0.61
    lict
    -0.61
    vati
    -0.59
    UFF
    -0.58
    Pool
    -0.58
    Times
    -0.58
    ardless
    -0.57
    veyard
    -0.57
     centr
    -0.57
    POSITIVE LOGITS
     immediately
    1.01
     instinctively
    1.00
     exclaimed
    1.00
     instantly
    0.98
     alerted
    0.97
     exclaim
    0.96
     panic
    0.87
     intrigued
    0.87
     suspicion
    0.84
     rushed
    0.84
    Activations Density 2.059%

    No Known Activations