© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26411
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and investigations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    202
    +0.12
    0.6%
    534
    +0.11
    0.5%
    392
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.12
    0.06
    725
    +0.11
    0.05
    682
    +0.10
    0.05
    Negative Logits
     Babe
    -0.84
     Jagu
    -0.81
     chimpan
    -0.77
     Socialism
    -0.76
    culosis
    -0.75
     corrid
    -0.75
     Lovecraft
    -0.75
     executions
    -0.74
     miner
    -0.74
     abolition
    -0.73
    POSITIVE LOGITS
     Kislyak
    1.47
     Flynn
    1.39
     Sergey
    1.13
     contacts
    1.00
     Turkish
    0.98
    opoulos
    0.98
    Russian
    0.97
    Turkish
    0.93
     Kushner
    0.92
    lyak
    0.90
    Activations Density 1.296%

    No Known Activations