© 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. 30806
    Prev
    Next
    INDEX
    Explanations

    phrases indicating measurement and organizational actions

    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
    506
    +0.14
    0.7%
    69
    +0.12
    0.6%
    455
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.08
    588
    +0.12
    0.07
    455
    +0.11
    0.07
    Negative Logits
     Believe
    -0.75
     Canaver
    -0.72
     Rohing
    -0.68
     Spur
    -0.66
     Ezek
    -0.66
    0000000000000000
    -0.66
     Nguyen
    -0.65
     Lau
    -0.65
     Bucs
    -0.64
     Norn
    -0.63
    POSITIVE LOGITS
     customize
    1.02
     retrieve
    0.98
     organize
    0.97
     manipulate
    0.96
     calculate
    0.94
     troubles
    0.94
     manage
    0.94
     configure
    0.92
     retrieving
    0.92
     automate
    0.90
    Activations Density 0.852%

    No Known Activations