© 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 EvalsExportsinterp-engineNEWAPI 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. 31594
    Prev
    Next
    INDEX
    Explanations

    elements related to battery life and charging efficiency

    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
    477
    +0.13
    0.6%
    464
    +0.12
    0.5%
    537
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.13
    0.09
    326
    +0.12
    0.10
    475
    +0.11
    0.04
    Negative Logits
     puppet
    -1.03
     pupp
    -0.92
     chess
    -0.85
     Osw
    -0.82
     Hispan
    -0.82
     Gould
    -0.81
     Chess
    -0.81
     Hitchcock
    -0.78
     Puppet
    -0.78
     Robertson
    -0.77
    POSITIVE LOGITS
     recharge
    1.90
     batteries
    1.89
     lithium
    1.80
     battery
    1.77
    Battery
    1.70
     charger
    1.68
     Lith
    1.65
     Battery
    1.63
    Charg
    1.56
    Charge
    1.54
    Activations Density 1.590%

    No Known Activations