© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES_POST_32K-OAI
    11. 29627
    Prev
    Next
    INDEX
    Explanations

    terms related to radiation and its effects

    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
    288
    +0.14
    0.6%
    649
    +0.12
    0.5%
    502
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.03
    325
    +0.12
    0.02
    634
    +0.11
    0.02
    Negative Logits
    lihood
    -1.03
    liness
    -0.79
    lier
    -0.78
    eenth
    -0.77
    aws
    -0.74
    theless
    -0.74
    thood
    -0.72
    HCR
    -0.72
    hire
    -0.72
    ijk
    -0.71
    POSITIVE LOGITS
     horm
    0.96
     doses
    0.91
     belts
    0.91
     dose
    0.90
    arding
    0.88
     shielding
    0.87
     sickness
    0.86
     iodine
    0.85
    arded
    0.81
     isot
    0.79
    Activations Density 0.131%

    No Known Activations