© 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. 9109
    Prev
    Next
    INDEX
    Explanations

    references to quantities and values related to financial or economic contexts

    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
    580
    +0.11
    0.5%
    497
    +0.09
    0.4%
    3
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.11
    0.03
    232
    +0.09
    0.03
    534
    +0.09
    0.02
    Negative Logits
     Flavoring
    -0.69
    abus
    -0.68
    WARE
    -0.67
     ILCS
    -0.65
    ebus
    -0.64
     "$:/
    -0.64
     dues
    -0.64
     dearly
    -0.63
     opera
    -0.63
     unsus
    -0.62
    POSITIVE LOGITS
    ciating
    1.02
    null
    1.01
    zero
    0.87
    ãĤ¨ãĥ«
    0.82
    tty
    0.81
    idated
    0.72
    ãĥĦ
    0.71
    db
    0.70
    disk
    0.68
    etheus
    0.67
    Activations Density 0.119%

    No Known Activations