© 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. 8-RES_POST_32K-OAI
    11. 8939
    Prev
    Next
    INDEX
    Explanations

    words related to group dynamics and collective experiences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    65
    +0.10
    0.5%
    373
    +0.10
    0.5%
    485
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.03
    284
    +0.10
    0.06
    232
    +0.10
    0.07
    Negative Logits
    staking
    -0.80
    kefeller
    -0.70
    forth
    -0.64
     Flood
    -0.64
    kell
    -0.62
    hesive
    -0.61
    blank
    -0.61
    panic
    -0.60
     Democr
    -0.60
    renheit
    -0.59
    POSITIVE LOGITS
    obos
    0.79
    uti
    0.66
    atche
    0.64
    oro
    0.63
     seiz
    0.63
    ¹
    0.62
    rocal
    0.62
    ikan
    0.61
     Yak
    0.61
    Ĥ¬
    0.61
    Activations Density 0.501%

    No Known Activations