© 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. 31983
    Prev
    Next
    INDEX
    Explanations

    topics related to marijuana legislation and its regulation

    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
    29
    +0.09
    0.4%
    134
    +0.09
    0.4%
    196
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.09
    0.04
    134
    +0.09
    0.05
    205
    +0.09
    0.03
    Negative Logits
     Titanic
    -1.06
     MSI
    -0.89
     pengu
    -0.86
     Hebdo
    -0.84
    leigh
    -0.83
     Nets
    -0.81
     Ultron
    -0.81
     Stevens
    -0.80
     Nikon
    -0.79
    åĭ
    -0.78
    POSITIVE LOGITS
     Cannabis
    2.17
     cannabis
    2.16
     Marijuana
    2.13
     marijuana
    2.10
    arijuana
    2.08
     THC
    1.99
     dispensary
    1.89
     dispensaries
    1.86
     legalization
    1.83
     cannabinoids
    1.78
    Activations Density 3.706%

    No Known Activations