© 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. 31051
    Prev
    Next
    INDEX
    Explanations

    commands related to configuring system settings or parameters

    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
    666
    +0.10
    0.5%
    754
    +0.10
    0.5%
    694
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.03
    448
    +0.10
    0.02
    514
    +0.10
    0.02
    Negative Logits
    eous
    -0.65
    ettes
    -0.62
    mond
    -0.60
    oard
    -0.60
    earth
    -0.59
     Neh
    -0.57
     Methodist
    -0.56
     punches
    -0.56
     Sacrament
    -0.56
     Sacrifice
    -0.55
    POSITIVE LOGITS
    uid
    1.01
    variable
    0.96
    Timeout
    0.94
    ThumbnailImage
    0.93
    attr
    0.89
    env
    0.88
    priority
    0.87
    Enabled
    0.86
    upt
    0.84
    tle
    0.83
    Activations Density 0.117%

    No Known Activations