© 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. 10-RES_POST_32K-OAI
    11. 30205
    Prev
    Next
    INDEX
    Explanations

    concepts related to financial transactions and currency values

    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
    246
    +0.10
    0.5%
    364
    +0.10
    0.5%
    740
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.10
    0.02
    529
    +0.10
    0.03
    674
    +0.10
    0.03
    Negative Logits
     therapists
    -0.85
     POV
    -0.84
     therapist
    -0.83
     Airbnb
    -0.82
     Skype
    -0.82
    plugins
    -0.78
     Kinect
    -0.76
     roommate
    -0.76
    Netflix
    -0.76
    âĶĢâĶĢâĶĢâĶĢ
    -0.75
    POSITIVE LOGITS
     coins
    1.88
     mint
    1.82
     coin
    1.82
     Coins
    1.64
     Coin
    1.63
     Mint
    1.59
     denomination
    1.57
     denominations
    1.57
    Coin
    1.51
     counterfe
    1.43
    Activations Density 1.327%

    No Known Activations