© 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. 10-RES_POST_32K-OAI
    11. 29410
    Prev
    Next
    INDEX
    Explanations

    references to research and academic centers

    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
    224
    +0.11
    0.5%
    752
    +0.10
    0.5%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.03
    596
    +0.10
    0.03
    648
    +0.10
    0.03
    Negative Logits
     Luthor
    -0.74
     Qiao
    -0.73
    wcsstore
    -0.69
    ths
    -0.66
    aceae
    -0.64
     Flask
    -0.62
    cffffcc
    -0.62
     Rowling
    -0.61
    soDeliveryDate
    -0.60
    IGHTS
    -0.59
    POSITIVE LOGITS
    pieces
    1.13
    piece
    1.01
    ologies
    0.90
    fold
    0.83
    itect
    0.81
    fire
    0.79
     pamph
    0.78
    maid
    0.77
    point
    0.77
    tyard
    0.76
    Activations Density 0.243%

    No Known Activations