© 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. 30913
    Prev
    Next
    INDEX
    Explanations

    terms related to officiating and authoritative roles

    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
    118
    +0.11
    0.5%
    263
    +0.10
    0.4%
    688
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.03
    314
    +0.10
    -0.00
    588
    +0.09
    0.03
    Negative Logits
    wana
    -0.73
    è£ħ
    -0.72
     Tate
    -0.67
    trap
    -0.65
    âĻ¥
    -0.65
    ADD
    -0.63
    Recommended
    -0.62
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.61
    =-=-=-=-=-=-=-=-
    -0.60
     bashing
    -0.59
    POSITIVE LOGITS
    ially
    1.83
    ials
    1.26
    ial
    1.17
    IAL
    1.13
    iate
    1.11
    iated
    1.08
    iating
    1.06
    aneously
    1.04
    inar
    1.01
    aneous
    1.00
    Activations Density 0.154%

    No Known Activations