© 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. 9103
    Prev
    Next
    INDEX
    Explanations

    phrases related to meaningful and promotional content that focuses on journalism and social issues

    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
    +0.17
    0.8%
    430
    +0.13
    0.6%
    732
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.17
    0.05
    759
    +0.13
    0.06
    675
    +0.11
    0.06
    Negative Logits
    pmwiki
    -0.72
     coerc
    -0.67
     IPM
    -0.62
    SPONSORED
    -0.59
    lihood
    -0.58
     defic
    -0.58
     Donation
    -0.57
     Pupp
    -0.57
    naire
    -0.56
    Joined
    -0.56
    POSITIVE LOGITS
    gon
    0.64
    osion
    0.61
    pload
    0.59
    steamapps
    0.55
    perate
    0.55
    Ĵ
    0.55
    icol
    0.55
    owl
    0.54
    xi
    0.54
    ache
    0.54
    Activations Density 0.487%

    No Known Activations