© 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. 30196
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to neural activity and holography

    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
    313
    +0.12
    0.5%
    708
    +0.10
    0.5%
    90
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.12
    365
    +0.10
    0.00
    156
    +0.10
    0.06
    Negative Logits
    elf
    -0.75
    emade
    -0.75
    editor
    -0.74
    Pocket
    -0.73
    ilton
    -0.71
    Books
    -0.70
    Kit
    -0.69
    info
    -0.69
    Help
    -0.69
    password
    -0.68
    POSITIVE LOGITS
     phase
    1.71
     phases
    1.68
     cycles
    1.56
     periods
    1.51
     cycle
    1.48
    phase
    1.45
     peaks
    1.44
     Phase
    1.43
    Phase
    1.41
     amplitude
    1.41
    Activations Density 4.984%

    No Known Activations