© 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. 30644
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to various entities and characters

    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
    211
    +0.10
    0.5%
    87
    +0.10
    0.5%
    464
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.10
    -0.02
    480
    +0.10
    0.04
    266
    +0.09
    0.05
    Negative Logits
    icas
    -0.66
    bett
    -0.65
    abet
    -0.62
    agos
    -0.59
    opic
    -0.58
    ullivan
    -0.57
    odo
    -0.56
    rium
    -0.55
    utherland
    -0.55
    apo
    -0.54
    POSITIVE LOGITS
     Gleaming
    1.00
     Awoken
    0.97
     Dragonbound
    0.92
     Primordial
    0.91
    ahime
    0.90
     Reincarnated
    0.90
     è£ı
    0.88
     Minotaur
    0.87
     ç¥ŀ
    0.83
     Slime
    0.82
    Activations Density 0.423%

    No Known Activations