© 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. 30340
    Prev
    Next
    INDEX
    Explanations

    references to government entities and political affiliations

    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
    362
    +0.12
    0.6%
    420
    +0.10
    0.4%
    752
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.12
    0.12
    152
    +0.10
    0.10
    67
    +0.10
    0.09
    Negative Logits
    anse
    -0.89
    ouf
    -0.78
    isode
    -0.78
    ailable
    -0.76
    astery
    -0.74
    estamp
    -0.74
    cific
    -0.72
    ixture
    -0.71
    unction
    -0.71
    artment
    -0.70
    POSITIVE LOGITS
     officials
    1.54
     prosecutors
    1.42
     lawmakers
    1.39
     regulators
    1.38
     investigators
    1.38
     negotiators
    1.34
     authorities
    1.33
     policymakers
    1.28
     critics
    1.26
     aides
    1.24
    Activations Density 0.882%

    No Known Activations