© 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. 30776
    Prev
    Next
    INDEX
    Explanations

    phrases related to astronomical imagery and discoveries

    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
    373
    +0.16
    0.8%
    494
    +0.10
    0.5%
    108
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    631
    +0.16
    0.02
    373
    +0.10
    -0.01
    586
    +0.10
    0.02
    Negative Logits
    ariat
    -0.71
    arios
    -0.70
    ibaba
    -0.70
    terness
    -0.69
    bane
    -0.69
    otine
    -0.66
     Idle
    -0.64
    ACP
    -0.64
    yss
    -0.64
    ilts
    -0.63
    POSITIVE LOGITS
     Nasa
    1.00
     Scientists
    0.75
    Science
    0.75
     Researchers
    0.71
     scientists
    0.70
    NASA
    0.70
     astronomers
    0.70
     researchers
    0.70
    Scientists
    0.70
     Hubble
    0.68
    Activations Density 0.068%

    No Known Activations