© 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. 8-RES_POST_32K-OAI
    11. 7066
    Prev
    Next
    INDEX
    Explanations

    references to military ranks, specifically "Lieutenant" and its abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    192
    +0.11
    0.5%
    515
    +0.10
    0.5%
    537
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.11
    0.02
    192
    +0.10
    0.01
    629
    +0.10
    0.01
    Negative Logits
    BOOK
    -0.86
    icles
    -0.82
    fulness
    -0.75
    utic
    -0.74
    mos
    -0.70
    metic
    -0.63
    heet
    -0.62
    issors
    -0.61
    iris
    -0.61
    places
    -0.60
    POSITIVE LOGITS
     colonel
    1.25
     Colonel
    1.14
    utenant
    1.11
     Commander
    0.96
    seless
    0.84
    escription
    0.82
     Governor
    0.81
    geant
    0.76
     Command
    0.75
    chief
    0.75
    Activations Density 0.039%

    No Known Activations