© 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. 10-RES_POST_32K-OAI
    11. 28976
    Prev
    Next
    INDEX
    Explanations

    terms related to health and medical conditions involving affecting levels in various contexts

    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
    362
    +0.13
    0.6%
    405
    +0.10
    0.5%
    621
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.13
    0.09
    123
    +0.10
    0.10
    469
    +0.10
    0.09
    Negative Logits
     Flavoring
    -0.81
    CLASSIFIED
    -0.79
    sbm
    -0.75
    soDeliveryDate
    -0.71
    DAQ
    -0.68
    ãĥķãĤ©
    -0.68
    wcsstore
    -0.67
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.67
     incorpor
    -0.66
    oku
    -0.66
    POSITIVE LOGITS
     vitro
    1.40
     vivo
    1.27
     rodents
    1.25
     humans
    1.25
     mice
    1.21
     rats
    1.20
    ulin
    1.20
    activate
    1.17
    activation
    1.15
     rabbits
    1.14
    Activations Density 0.679%

    No Known Activations