© 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. 5224
    Prev
    Next
    INDEX
    Explanations

    references to liberal arts and liberal ideologies

    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
    18
    +0.13
    0.6%
    288
    +0.10
    0.5%
    44
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.13
    0.04
    32
    +0.10
    0.03
    288
    +0.09
    0.03
    Negative Logits
    iru
    -0.72
     Blazing
    -0.71
     Saga
    -0.70
    BLE
    -0.64
     Redemption
    -0.63
    senal
    -0.62
     Danger
    -0.60
     Dragons
    -0.58
    Gi
    -0.58
    gpu
    -0.57
    POSITIVE LOGITS
     arts
    0.98
    izing
    0.85
    ization
    0.83
    esse
    0.82
    izations
    0.80
    nesota
    0.76
     Democrat
    0.76
    itarian
    0.74
    neapolis
    0.73
    izes
    0.73
    Activations Density 0.070%

    No Known Activations