© 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 EvalsExportsinterp-engineNEWAPI 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. 32339
    Prev
    Next
    INDEX
    Explanations

    mentions of love and romantic relationships

    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
    404
    +0.12
    0.6%
    16
    +0.12
    0.6%
    186
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    513
    +0.12
    0.02
    317
    +0.12
    0.02
    531
    +0.10
    0.03
    Negative Logits
     Gork
    -0.83
     Canaver
    -0.75
    ulhu
    -0.68
    arian
    -0.65
    TPPStreamerBot
    -0.65
     Horizon
    -0.65
     Psychiatric
    -0.62
     Rampage
    -0.62
    ħĭ
    -0.62
     Brands
    -0.61
    POSITIVE LOGITS
    making
    1.15
    interest
    1.03
    birds
    1.00
     affair
    0.95
    child
    0.95
     interest
    0.93
     triangle
    0.92
     triangles
    0.88
    fruit
    0.88
    letters
    0.87
    Activations Density 0.160%

    No Known Activations