© 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. 10-RES_POST_32K-OAI
    11. 29551
    Prev
    Next
    INDEX
    Explanations

    phrases that express quantity or frequency

    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
    446
    +0.14
    0.6%
    97
    +0.10
    0.5%
    645
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.14
    0.06
    645
    +0.10
    0.06
    344
    +0.10
    0.07
    Negative Logits
    è£ħ
    -0.83
     è£ıç
    -0.72
    utonium
    -0.72
    éĹĺ
    -0.70
    andise
    -0.66
    ãĤ´ãĥ³
    -0.65
    ailability
    -0.61
    £ı
    -0.61
     Provided
    -0.60
    contained
    -0.60
    POSITIVE LOGITS
     times
    1.31
     people
    1.28
     guys
    1.25
     folks
    1.19
     kids
    1.04
    entimes
    0.99
     moms
    0.99
     teenagers
    0.98
     dudes
    0.97
     peoples
    0.97
    Activations Density 0.749%

    No Known Activations