© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29446
    Prev
    Next
    INDEX
    Explanations

    mentions of orchestras and related musical terms

    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
    218
    +0.12
    0.5%
    131
    +0.10
    0.4%
    679
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    -0.00
    613
    +0.10
    0.01
    232
    +0.10
    0.01
    Negative Logits
     Mississ
    -0.71
     ink
    -0.67
     Mehran
    -0.66
     Leone
    -0.65
     Goods
    -0.64
     Newfoundland
    -0.64
    unks
    -0.63
     Scotia
    -0.63
     WARN
    -0.62
     Canadians
    -0.61
    POSITIVE LOGITS
    ĭ
    1.30
    Ĩ
    1.22
    ļ
    1.17
    ļé
    1.05
    ¤
    1.04
    Į
    1.03
    ķ
    1.03
    İ
    1.00
    Ľ
    0.99
    §
    0.99
    Activations Density 0.075%

    No Known Activations