© 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. 8-RES_POST_32K-OAI
    11. 4460
    Prev
    Next
    INDEX
    Explanations

    references to a specific person or entity denoted by the abbreviation "Cl."

    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
    314
    +0.15
    0.7%
    16
    +0.10
    0.5%
    223
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    588
    +0.15
    0.03
    137
    +0.10
    0.02
    493
    +0.10
    0.03
    Negative Logits
     Trilogy
    -0.73
     Reloaded
    -0.66
     Fellowship
    -0.65
     err
    -0.63
     SPD
    -0.62
     Prelude
    -0.62
    lihood
    -0.62
     htt
    -0.61
     Updates
    -0.60
     plural
    -0.59
    POSITIVE LOGITS
    utch
    1.18
    osure
    1.08
    oser
    1.06
    imb
    1.06
    ients
    1.06
    iffs
    1.04
    apping
    0.99
    ipping
    0.98
    ashing
    0.98
    andestine
    0.98
    Activations Density 0.057%

    No Known Activations