© 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. 8-RES_POST_32K-OAI
    11. 8101
    Prev
    Next
    INDEX
    Explanations

    sequences related to ordinal numbers and their references

    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
    221
    +0.11
    0.5%
    542
    +0.10
    0.5%
    697
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.11
    0.09
    408
    +0.10
    0.11
    402
    +0.10
    0.07
    Negative Logits
    iquette
    -0.81
    ouls
    -0.73
     subconscious
    -0.72
    roxy
    -0.72
     Shutterstock
    -0.59
    Pinterest
    -0.59
    yrics
    -0.59
     limitless
    -0.58
    Engineers
    -0.58
    Loading
    -0.58
    POSITIVE LOGITS
     latter
    1.08
     respective
    0.90
     trio
    0.85
     installments
    0.85
     pair
    0.84
    ilogy
    0.83
     case
    0.81
    emate
    0.80
     cases
    0.79
     CASE
    0.79
    Activations Density 1.581%

    No Known Activations