© 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. 30461
    Prev
    Next
    INDEX
    Explanations

    temporal references and expressions related to time and future events

    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
    756
    +0.14
    0.6%
    338
    +0.12
    0.6%
    91
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.14
    0.00
    241
    +0.12
    0.06
    724
    +0.10
    0.10
    Negative Logits
    iasis
    -0.71
    sth
    -0.66
    clud
    -0.66
     CoC
    -0.61
    wik
    -0.61
     Mechdragon
    -0.60
     Donation
    -0.60
    GF
    -0.58
     Difficulty
    -0.57
    SourceFile
    -0.57
    POSITIVE LOGITS
     tomorrow
    1.82
     Tomorrow
    1.40
    Tomorrow
    1.36
     2050
    1.31
     2030
    1.31
     2025
    1.25
     2020
    1.22
     2022
    1.22
     forever
    1.22
     2024
    1.21
    Activations Density 2.353%

    No Known Activations