© 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. 32471
    Prev
    Next
    INDEX
    Explanations

    references to significant events or mentions of public figures

    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
    329
    +0.15
    0.7%
    126
    +0.11
    0.5%
    736
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    440
    +0.15
    0.06
    738
    +0.11
    0.04
    326
    +0.10
    0.17
    Negative Logits
     Kel
    -0.91
    kaya
    -0.89
     Dalton
    -0.86
    Ari
    -0.84
    igi
    -0.82
    oglu
    -0.82
     Lerner
    -0.81
     Mig
    -0.80
    Putin
    -0.79
     DV
    -0.76
    POSITIVE LOGITS
     Sw
    2.45
    Sw
    2.30
    sw
    2.21
     SW
    2.06
     sw
    2.04
    SW
    1.94
     Swap
    1.50
     Swan
    1.43
     Swanson
    1.42
     Swarm
    1.37
    Activations Density 5.538%

    No Known Activations