© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5586
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the concept of remaining or staying in a particular state or condition

    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
    715
    +0.12
    0.6%
    55
    +0.11
    0.5%
    566
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    715
    +0.12
    0.04
    567
    +0.11
    0.03
    469
    +0.10
    0.03
    Negative Logits
    ology
    -0.65
     twists
    -0.65
     slideshow
    -0.65
     Taxes
    -0.64
    uyomi
    -0.63
    fulness
    -0.62
    comings
    -0.61
     ripple
    -0.61
     goodbye
    -0.61
    ough
    -0.60
    POSITIVE LOGITS
     aware
    1.12
     confident
    1.02
     obsessed
    0.99
     grateful
    0.98
     immersed
    0.98
     addicted
    0.98
     convinced
    0.98
     thankful
    0.96
     acquainted
    0.94
     vigilant
    0.93
    Activations Density 0.075%

    No Known Activations