© 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. 31019
    Prev
    Next
    INDEX
    Explanations

    phrases that prompt viewing or watching content, particularly videos

    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
    380
    +0.10
    0.5%
    373
    +0.10
    0.5%
    744
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.10
    0.05
    97
    +0.10
    0.03
    500
    +0.10
    0.04
    Negative Logits
     arrang
    -0.74
    etheless
    -0.74
     screws
    -0.65
    recy
    -0.65
    athered
    -0.65
     horizont
    -0.64
     affili
    -0.64
    yrinth
    -0.64
     sins
    -0.63
     acron
    -0.63
    POSITIVE LOGITS
     above
    0.90
     below
    0.85
     Video
    0.80
     Highlights
    0.79
     highlights
    0.78
    above
    0.75
     VICE
    0.75
     VIDEO
    0.74
    :'
    0.74
     LIVE
    0.73
    Activations Density 0.688%

    No Known Activations