© 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. 28281
    Prev
    Next
    INDEX
    Explanations

    statistics and details about young adults and their health insurance coverage

    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
    241
    +0.11
    0.5%
    18
    +0.11
    0.5%
    106
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.11
    0.09
    488
    +0.11
    0.08
    86
    +0.11
    0.07
    Negative Logits
    eals
    -0.83
    tainment
    -0.78
    Ü
    -0.68
     awaits
    -0.64
    ratulations
    -0.63
     comrade
    -0.62
     brill
    -0.62
     tsun
    -0.61
    yip
    -0.60
    forcement
    -0.59
    POSITIVE LOGITS
     aged
    1.34
     surveyed
    1.22
     ages
    1.15
     polled
    1.13
     nationally
    1.02
     born
    1.01
     age
    0.99
     65
    0.98
     earning
    0.96
     enrolled
    0.94
    Activations Density 0.614%

    No Known Activations