© 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. 31555
    Prev
    Next
    INDEX
    Explanations

    references to political instability and violence

    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
    183
    +0.09
    0.4%
    390
    +0.09
    0.4%
    507
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.09
    0.27
    640
    +0.09
    0.20
    145
    +0.09
    0.18
    Negative Logits
     Whitney
    -0.95
     Garfield
    -0.87
     Hampton
    -0.87
     Rutherford
    -0.87
     Brady
    -0.86
     Whitman
    -0.84
     Floyd
    -0.83
     Webster
    -0.83
     Gillespie
    -0.83
     Stanton
    -0.83
    POSITIVE LOGITS
     NGOs
    1.20
     Ankara
    1.19
     Jakarta
    1.18
     NGO
    1.18
     Erit
    1.13
     Bulgarian
    1.10
     Bulgaria
    1.10
     Armenia
    1.09
    Turkey
    1.07
    ÅŁ
    1.06
    Activations Density 1.848%

    No Known Activations