© 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. 28870
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets in text

    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
    703
    +0.27
    1.4%
    142
    +0.18
    0.9%
    77
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.27
    0.05
    640
    +0.18
    0.04
    672
    +0.12
    0.02
    Negative Logits
    SPONSORED
    -1.46
    Advertisements
    -1.38
    Lago
    -1.35
    HM
    -1.27
    ${
    -1.25
    Regular
    -1.24
    Lua
    -1.23
    IU
    -1.23
    Route
    -1.22
    Large
    -1.22
    POSITIVE LOGITS
     pione
    1.07
     eleph
    1.06
     citiz
    0.92
     metic
    0.91
     Fore
    0.91
     subur
    0.87
     earthqu
    0.86
     DC
    0.86
     Derby
    0.83
     Gem
    0.82
    Activations Density 0.145%

    No Known Activations