© 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 EvalsExportsinterp-engineNEWAPI 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. 32553
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "in the."

    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
    232
    +0.14
    0.6%
    530
    +0.13
    0.6%
    84
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.06
    476
    +0.13
    0.03
    530
    +0.12
    0.04
    Negative Logits
     promot
    -0.77
     exhib
    -0.75
    minist
    -0.72
     seiz
    -0.72
     administr
    -0.71
     tampering
    -0.71
     challeng
    -0.70
     secondly
    -0.70
     applic
    -0.70
     applicable
    -0.69
    POSITIVE LOGITS
     Moonlight
    1.03
     Paradise
    1.02
     Midnight
    0.99
    ĨĴ
    0.97
     Sunshine
    0.93
     Eternity
    0.92
     Atlantis
    0.90
     Avalon
    0.90
     Love
    0.89
     Heaven
    0.89
    Activations Density 0.353%

    No Known Activations