© 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. 28923
    Prev
    Next
    INDEX
    Explanations

    equations or mathematical expressions

    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
    640
    +0.13
    0.6%
    314
    +0.13
    0.6%
    326
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.13
    0.03
    289
    +0.13
    0.02
    326
    +0.10
    0.03
    Negative Logits
    eness
    -0.82
    wright
    -0.74
    mates
    -0.73
    esis
    -0.73
    itage
    -0.72
    unia
    -0.71
     contrace
    -0.70
    iates
    -0.69
    eding
    -0.68
    iate
    -0.67
    POSITIVE LOGITS
    ========
    2.13
    ============
    1.99
    ===
    1.53
    ======
    0.91
    ====
    0.91
    ãĥ´ãĤ¡
    0.91
    -+-+-+-+
    0.84
    ãĥīãĥ©ãĤ´ãĥ³
    0.82
    ãĤ¨ãĥ«
    0.82
     TRUE
    0.81
    Activations Density 0.184%

    No Known Activations