© 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. 8-RES_POST_32K-OAI
    11. 6544
    Prev
    Next
    INDEX
    Explanations

    mentions of punishment and related terms

    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
    +0.12
    0.5%
    96
    +0.10
    0.5%
    63
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.12
    0.02
    35
    +0.10
    0.02
    301
    +0.09
    0.01
    Negative Logits
    gow
    -0.79
    yip
    -0.71
    ortment
    -0.69
    regor
    -0.66
     Fargo
    -0.66
     Pegasus
    -0.65
    clus
    -0.64
    otle
    -0.63
    opher
    -0.62
    sie
    -0.62
    POSITIVE LOGITS
     inflicted
    0.94
     harshly
    0.91
     punishments
    0.82
     punished
    0.73
     sanction
    0.72
     severely
    0.72
    ishable
    0.72
     punishment
    0.70
     accordingly
    0.69
     regimes
    0.68
    Activations Density 0.039%

    No Known Activations