© 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. 29811
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "why."

    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
    572
    +0.14
    0.6%
    628
    +0.10
    0.4%
    279
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.14
    0.05
    572
    +0.10
    0.05
    9
    +0.10
    0.03
    Negative Logits
    interstitial
    -0.89
    20439
    -0.71
    ãĤ¤ãĥĪ
    -0.70
    culosis
    -0.64
    capacity
    -0.61
    ival
    -0.58
    phrine
    -0.58
     adjud
    -0.57
    è¦ļéĨĴ
    -0.56
     safest
    -0.56
    POSITIVE LOGITS
    'd
    0.88
    yy
    0.78
     didnt
    0.71
     me
    0.70
     didn
    0.70
    Dat
    0.69
    !?
    0.67
    didn
    0.66
    ENSE
    0.66
    're
    0.65
    Activations Density 0.120%

    No Known Activations