© 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. 28968
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions indicating relationships or conditions

    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
    369
    +0.12
    0.5%
    91
    +0.10
    0.5%
    494
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.12
    0.19
    22
    +0.10
    0.16
    469
    +0.10
    0.14
    Negative Logits
     Miko
    -0.72
    âĿ
    -0.69
    etheless
    -0.68
    hya
    -0.65
    raf
    -0.62
    AAA
    -0.62
    apses
    -0.61
    AUT
    -0.61
     Logged
    -0.61
    Champ
    -0.61
    POSITIVE LOGITS
     order
    1.82
     hopes
    1.51
     anticipation
    1.36
     response
    1.27
     preparation
    1.26
     lieu
    1.24
     pursuit
    1.24
     retaliation
    1.18
     attempt
    1.17
     exchange
    1.14
    Activations Density 1.242%

    No Known Activations