© 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 EvalsExportsinterp-engineNEWAPI 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. 31699
    Prev
    Next
    INDEX
    Explanations

    instances of the word "drop" and its variations, indicating a focus on changes or transitions

    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
    402
    +0.13
    0.6%
    298
    +0.11
    0.5%
    274
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.13
    0.04
    366
    +0.11
    0.03
    274
    +0.10
    0.03
    Negative Logits
    asus
    -0.78
    eway
    -0.76
    cession
    -0.75
    iola
    -0.73
    storage
    -0.70
    uncture
    -0.66
    oly
    -0.64
    Storage
    -0.64
    eur
    -0.64
    eways
    -0.64
    POSITIVE LOGITS
     bombshell
    1.27
     hints
    1.18
     bombs
    1.14
     leaflets
    0.98
     jaws
    0.90
     overboard
    0.84
     anchor
    0.82
     dead
    0.81
     pounds
    0.81
     bomb
    0.79
    Activations Density 0.407%

    No Known Activations