© 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. 8-RES_POST_32K-OAI
    11. 7760
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to legislative and regulatory frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    35
    +0.11
    0.5%
    159
    +0.10
    0.4%
    756
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.08
    362
    +0.10
    0.07
    507
    +0.09
    0.07
    Negative Logits
     Sawyer
    -0.65
    spell
    -0.65
    Champ
    -0.64
     Finder
    -0.63
    pedia
    -0.62
     Kinn
    -0.62
    Revolution
    -0.61
     Irwin
    -0.60
    Plot
    -0.59
    Cmd
    -0.58
    POSITIVE LOGITS
     regulating
    0.88
     commerce
    0.83
     behavior
    0.81
     dealing
    0.80
     handling
    0.78
     behaviour
    0.77
     conduct
    0.76
     respecting
    0.74
     greenhouse
    0.72
     permissible
    0.72
    Activations Density 0.923%

    No Known Activations