© 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. 27810
    Prev
    Next
    INDEX
    Explanations

    specific formats, categories, or types of media and their documentation

    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
    145
    +0.11
    0.5%
    52
    +0.11
    0.5%
    250
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.11
    0.06
    326
    +0.11
    0.05
    224
    +0.10
    0.04
    Negative Logits
    PB
    -0.92
    NK
    -0.89
    RH
    -0.87
    actionDate
    -0.86
    soDeliveryDate
    -0.83
     carbohyd
    -0.80
    BTC
    -0.79
    JB
    -0.78
    KC
    -0.78
    inventoryQuantity
    -0.75
    POSITIVE LOGITS
     =================
    0.95
     =================================
    0.92
     =================================================================
    0.83
     Manufacturer
    0.81
     Print
    0.80
     ----------------
    0.79
    ************
    0.78
    -----
    0.78
     OF
    0.76
     Included
    0.75
    Activations Density 0.336%

    No Known Activations