© 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. 8-RES_POST_32K-OAI
    11. 5590
    Prev
    Next
    INDEX
    Explanations

    descriptive language related to food, flavor, and culinary experiences

    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
    478
    +0.10
    0.5%
    750
    +0.10
    0.5%
    225
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.10
    0.12
    575
    +0.10
    0.13
    288
    +0.10
    0.14
    Negative Logits
    otent
    -0.74
    iban
    -0.71
    administ
    -0.71
    lem
    -0.70
    initial
    -0.70
    arten
    -0.69
    visory
    -0.68
    avier
    -0.68
    odan
    -0.67
    ensor
    -0.65
    POSITIVE LOGITS
     awaits
    1.15
     await
    1.09
     abound
    1.09
     lurking
    0.92
     happening
    0.90
     imaginable
    0.84
     goodies
    0.84
     discoveries
    0.82
     happen
    0.81
     treasures
    0.81
    Activations Density 2.300%

    No Known Activations