© 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. 5574
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "for" indicating purpose or intent

    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
    314
    +0.20
    0.9%
    581
    +0.12
    0.6%
    663
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.20
    0.07
    570
    +0.12
    0.04
    641
    +0.12
    0.06
    Negative Logits
     Machina
    -0.71
     Lori
    -0.66
     Donovan
    -0.64
     Pelosi
    -0.63
     him
    -0.62
     Marcos
    -0.61
     Schultz
    -0.60
     Melody
    -0.60
     Goodbye
    -0.60
     Moj
    -0.60
    POSITIVE LOGITS
     purposes
    0.98
     guiActiveUn
    0.94
    ancial
    0.93
    aceutical
    0.87
     reasons
    0.85
    utical
    0.81
    vernment
    0.81
    advertising
    0.77
     purpose
    0.77
    apons
    0.76
    Activations Density 0.321%

    No Known Activations