© 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. 28903
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or names associated with exploration or travel

    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
    463
    +0.10
    0.4%
    327
    +0.09
    0.4%
    545
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.10
    0.01
    396
    +0.09
    0.03
    22
    +0.09
    0.04
    Negative Logits
    paio
    -0.79
    arb
    -0.76
    abee
    -0.75
    okane
    -0.74
     recharge
    -0.74
    rays
    -0.72
    bat
    -0.72
    ercise
    -0.71
    ebus
    -0.71
    onduct
    -0.71
    POSITIVE LOGITS
     World
    2.19
    World
    2.11
    world
    2.07
     WORLD
    2.06
     world
    1.89
     Worlds
    1.80
     worlds
    1.67
     globe
    1.57
     Global
    1.56
     global
    1.56
    Activations Density 1.760%

    No Known Activations