© 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. 8-RES_POST_32K-OAI
    11. 8962
    Prev
    Next
    INDEX
    Explanations

    terms related to addiction and drug use within health contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    333
    +0.12
    0.5%
    12
    +0.11
    0.5%
    748
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.12
    0.03
    570
    +0.11
    0.01
    699
    +0.11
    0.01
    Negative Logits
    ufact
    -1.02
    peria
    -0.78
    ruary
    -0.75
    ospace
    -0.70
    ulia
    -0.70
    heit
    -0.70
    ippi
    -0.68
    alty
    -0.67
    illac
    -0.66
    ield
    -0.66
    POSITIVE LOGITS
     Ort
    0.66
    çĽ
    0.62
     Blazing
    0.61
     iron
    0.60
     bearings
    0.59
     screws
    0.57
    mud
    0.56
     prope
    0.56
    Amount
    0.55
     Dynamics
    0.55
    Activations Density 0.162%

    No Known Activations