© 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. 30722
    Prev
    Next
    INDEX
    Explanations

    specific numerical patterns and dates within texts

    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
    442
    +0.21
    1.0%
    160
    +0.18
    0.9%
    314
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.21
    0.06
    442
    +0.18
    0.05
    107
    +0.17
    0.04
    Negative Logits
     350
    -0.99
     343
    -0.97
     432
    -0.96
     640
    -0.94
     435
    -0.93
     45
    -0.93
     451
    -0.93
     512
    -0.92
     72
    -0.92
     42
    -0.92
    POSITIVE LOGITS
    2008
    1.59
    2009
    1.59
    2004
    1.58
    2010
    1.58
    2011
    1.58
    2013
    1.57
    2012
    1.57
    2007
    1.57
    1997
    1.56
    2014
    1.56
    Activations Density 0.181%

    No Known Activations