© 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. 29643
    Prev
    Next
    INDEX
    Explanations

    key moments of anticipation and excitement in narratives

    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
    56
    +0.12
    0.5%
    382
    +0.09
    0.4%
    203
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.17
    159
    +0.09
    0.12
    408
    +0.09
    0.17
    Negative Logits
    PLIED
    -0.88
     inconsist
    -0.81
    mbuds
    -0.74
     periodically
    -0.74
    ricted
    -0.74
    Recommended
    -0.74
    conservancy
    -0.73
    APD
    -0.72
    ©¶æ¥µ
    -0.72
    Downloadha
    -0.72
    POSITIVE LOGITS
     showdown
    1.28
     breakthrough
    1.28
     opportunity
    1.28
     reunion
    1.24
     moment
    1.20
     announcement
    1.19
     payoff
    1.18
     gamble
    1.15
     chance
    1.12
     coup
    1.10
    Activations Density 3.653%

    No Known Activations