© 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. 9017
    Prev
    Next
    INDEX
    Explanations

    references to totality or wholeness

    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
    528
    +0.11
    0.5%
    756
    +0.11
    0.5%
    660
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.11
    0.04
    528
    +0.11
    0.03
    626
    +0.11
    0.03
    Negative Logits
    aunts
    -0.87
    pas
    -0.85
    Tickets
    -0.83
    locks
    -0.83
    cards
    -0.76
    cook
    -0.74
    pages
    -0.74
    phones
    -0.73
    Keys
    -0.72
    MAX
    -0.72
    POSITIVE LOGITS
     constellation
    1.08
     society
    0.86
     humankind
    0.85
     worldview
    0.84
     nation
    0.83
     civilisation
    0.82
     phenomenon
    0.82
     civilization
    0.81
     swath
    0.81
     hemisphere
    0.81
    Activations Density 0.155%

    No Known Activations