© 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. 28924
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and user experience (UX) design

    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
    641
    +0.13
    0.6%
    315
    +0.11
    0.5%
    58
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.03
    61
    +0.11
    0.01
    104
    +0.10
    0.01
    Negative Logits
    76561
    -0.82
    say
    -0.82
    "]=>
    -0.80
    ":""},{"
    -0.78
    agara
    -0.77
     Witt
    -0.76
    aukee
    -0.75
    ocene
    -0.75
    epad
    -0.73
    @@@@@@@@
    -0.72
    POSITIVE LOGITS
    udeb
    1.11
     filesystem
    1.05
     modules
    0.85
     libraries
    0.83
     peripher
    0.82
    modules
    0.82
     library
    0.78
     ACPI
    0.78
     Utilities
    0.76
     PCI
    0.76
    Activations Density 0.110%

    No Known Activations