© 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. 30730
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and information disclosure

    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
    756
    +0.12
    0.5%
    1
    +0.11
    0.5%
    593
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.12
    0.03
    679
    +0.11
    0.13
    540
    +0.10
    0.11
    Negative Logits
     Roses
    -0.68
     Punch
    -0.67
     paddle
    -0.66
     Zed
    -0.65
     Runs
    -0.64
    Style
    -0.62
     treadmill
    -0.61
     Dice
    -0.61
     lashes
    -0.61
     piston
    -0.61
    POSITIVE LOGITS
     redacted
    1.31
     FOIA
    1.30
     databases
    1.26
     declass
    1.23
     archives
    1.23
     confidential
    1.19
     trove
    1.18
     archive
    1.15
    metadata
    1.13
     confidentiality
    1.11
    Activations Density 2.576%

    No Known Activations