© 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. 27222
    Prev
    Next
    INDEX
    Explanations

    time-related phrases and prepositions indicating periods of activity

    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
    218
    +0.14
    0.6%
    259
    +0.11
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.11
    611
    +0.11
    0.08
    608
    +0.11
    0.09
    Negative Logits
    paralle
    -0.65
    anamo
    -0.64
     redes
    -0.63
    aceutical
    -0.63
    worthiness
    -0.60
     spoiler
    -0.60
    ationally
    -0.58
     Vinyl
    -0.58
    chini
    -0.58
     contrace
    -0.56
    POSITIVE LOGITS
     morning
    1.68
     afternoon
    1.57
     evening
    1.55
     night
    1.41
     mornings
    1.39
    morning
    1.36
     evenings
    1.28
    Morning
    1.26
     nights
    1.23
     midday
    1.19
    Activations Density 0.882%

    No Known Activations