© 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. 30056
    Prev
    Next
    INDEX
    Explanations

    coding references and identifiers in programming contexts

    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
    388
    +0.13
    0.6%
    371
    +0.13
    0.6%
    326
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.14
    255
    +0.13
    0.12
    435
    +0.10
    0.08
    Negative Logits
     LEGO
    -1.01
     Aadhaar
    -0.99
     Tata
    -0.96
     Rao
    -0.91
     Vegeta
    -0.90
     Snapdragon
    -0.87
     Mayweather
    -0.83
     Devi
    -0.82
     Theresa
    -0.82
     HIP
    -0.82
    POSITIVE LOGITS
     Emacs
    1.84
     Vim
    1.52
     vim
    1.44
     Lisp
    1.38
    vim
    1.34
     buffers
    1.30
     buffer
    1.23
    acs
    1.15
     vi
    1.15
     ~/.
    1.14
    Activations Density 1.418%

    No Known Activations