© 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. 30093
    Prev
    Next
    INDEX
    Explanations

    references to budgetary proposals and financial policies

    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
    350
    +0.14
    0.6%
    163
    +0.11
    0.5%
    228
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.14
    0.13
    300
    +0.11
    0.13
    350
    +0.10
    0.10
    Negative Logits
    ĸļ
    -0.90
     Inquisition
    -0.88
    DragonMagazine
    -0.87
     Regist
    -0.80
     lia
    -0.80
     mosqu
    -0.80
    iquette
    -0.77
    aspers
    -0.74
     suscept
    -0.74
    atern
    -0.73
    POSITIVE LOGITS
     CBO
    1.27
     cuts
    1.18
     reductions
    1.14
     Budget
    1.12
     slashing
    1.11
    Republicans
    1.10
     proposals
    1.10
     Republicans
    1.09
     economists
    1.07
    usterity
    1.04
    Activations Density 6.112%

    No Known Activations