© 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. 8833
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving away or distributing items

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    508
    +0.11
    0.5%
    52
    +0.11
    0.5%
    329
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.11
    0.03
    688
    +0.11
    0.03
    250
    +0.11
    0.02
    Negative Logits
    itect
    -0.69
     Mong
    -0.65
    occup
    -0.63
    ansion
    -0.63
    quickShipAvailable
    -0.63
    abiding
    -0.63
    shore
    -0.62
    Dialogue
    -0.61
    ¨
    -0.61
    trak
    -0.61
    POSITIVE LOGITS
     refunds
    1.01
     generously
    0.97
     prizes
    0.94
     leaflets
    0.91
     gifts
    0.89
     vouchers
    0.87
     invitations
    0.85
     hairc
    0.83
     scholarships
    0.83
     awards
    0.82
    Activations Density 0.318%

    No Known Activations