© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29543
    Prev
    Next
    INDEX
    Explanations

    references to brightness or the concept of being light

    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
    459
    +0.14
    0.6%
    314
    +0.12
    0.5%
    628
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.03
    571
    +0.12
    0.03
    459
    +0.10
    0.02
    Negative Logits
    JUST
    -0.81
    sis
    -0.72
    ames
    -0.68
    cano
    -0.67
    ggle
    -0.65
    okia
    -0.63
    olls
    -0.61
    paces
    -0.61
     Kirin
    -0.61
    utical
    -0.61
    POSITIVE LOGITS
    hearted
    1.41
    weights
    1.32
    weight
    1.27
    years
    1.25
    heartedly
    1.08
    bul
    1.03
    ening
    0.99
    headed
    0.98
    nings
    0.94
    ning
    0.94
    Activations Density 0.124%

    No Known Activations