© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 32614
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulty or struggle in understanding or making decisions

    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
    718
    +0.12
    0.6%
    680
    +0.11
    0.5%
    205
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.12
    0.20
    551
    +0.11
    0.18
    718
    +0.11
    0.18
    Negative Logits
    Vis
    -0.68
     resid
    -0.66
    DragonMagazine
    -0.65
     prepares
    -0.64
     unfocusedRange
    -0.63
    naires
    -0.63
    ARA
    -0.63
     Hast
    -0.63
    stretched
    -0.62
     guiIcon
    -0.62
    POSITIVE LOGITS
     disagree
    1.04
     debunked
    0.98
     debunk
    0.97
     rebutt
    0.95
     impe
    0.93
     refute
    0.91
     argue
    0.91
     condem
    0.90
     arguing
    0.90
     dispro
    0.88
    Activations Density 1.732%

    No Known Activations