© 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. 8-RES_POST_32K-OAI
    11. 6248
    Prev
    Next
    INDEX
    Explanations

    phrases related to government policies and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    314
    +0.11
    0.5%
    496
    +0.10
    0.5%
    363
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.11
    0.10
    314
    +0.10
    0.03
    160
    +0.10
    0.07
    Negative Logits
     Arrows
    -0.77
     Voy
    -0.67
     Worlds
    -0.67
     Bows
    -0.63
     Empires
    -0.62
     Demons
    -0.62
     Beast
    -0.62
     Bolt
    -0.62
     Candle
    -0.61
     Shards
    -0.61
    POSITIVE LOGITS
    sponsored
    1.28
    funded
    1.26
    issued
    1.19
    approved
    1.17
    owned
    1.05
    provided
    1.04
     funded
    1.04
    supported
    1.03
    controlled
    1.02
    authorized
    1.01
    Activations Density 0.545%

    No Known Activations