© 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. 29843
    Prev
    Next
    INDEX
    Explanations

    variations of the letters "u" and sequences related to unique identifiers or names

    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
    211
    +0.14
    0.6%
    26
    +0.10
    0.4%
    281
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.14
    0.01
    659
    +0.10
    0.01
    211
    +0.09
    0.01
    Negative Logits
    yrus
    -0.67
     VIDEOS
    -0.65
    intent
    -0.58
    gdala
    -0.57
     Emin
    -0.57
    ebin
    -0.57
    ioned
    -0.57
     trave
    -0.57
     Pistons
    -0.56
    edly
    -0.56
    POSITIVE LOGITS
    pload
    1.01
    uge
    1.00
    uu
    0.94
    jin
    0.93
    hei
    0.93
    pta
    0.92
    ya
    0.85
    uthor
    0.84
    pport
    0.83
    ãĥĥãĥĪ
    0.82
    Activations Density 0.062%

    No Known Activations