© 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. 8877
    Prev
    Next
    INDEX
    Explanations

    words related to offerings, services, or products

    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
    453
    +0.10
    0.5%
    281
    +0.10
    0.5%
    694
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.10
    0.04
    688
    +0.10
    0.05
    279
    +0.10
    0.05
    Negative Logits
    DragonMagazine
    -0.82
    PsyNetMessage
    -0.79
    bell
    -0.78
    lie
    -0.77
    ogenesis
    -0.76
    pedia
    -0.72
     sidx
    -0.67
    wood
    -0.67
    icus
    -0.66
    adow
    -0.66
    POSITIVE LOGITS
     unparalleled
    1.01
     extensive
    0.98
     access
    0.98
     speedy
    0.98
     unlimited
    0.97
     exceptional
    0.94
     excellent
    0.93
     flexibility
    0.93
     instantaneous
    0.92
     comprehensive
    0.91
    Activations Density 0.364%

    No Known Activations