© 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. 5228
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to support for various causes and initiatives

    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
    362
    +0.13
    0.6%
    143
    +0.11
    0.5%
    646
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    646
    +0.13
    0.03
    78
    +0.11
    0.03
    143
    +0.10
    0.03
    Negative Logits
    æ©Ł
    -0.74
    epad
    -0.68
    killer
    -0.67
    iren
    -0.66
    rez
    -0.65
    mort
    -0.65
    pmwiki
    -0.65
    isphere
    -0.64
    mad
    -0.64
    olit
    -0.64
    POSITIVE LOGITS
     them
    0.81
     ongoing
    0.79
     him
    0.75
     their
    0.73
    ably
    0.72
     exemplary
    0.72
     us
    0.71
     efforts
    0.71
     upkeep
    0.71
     those
    0.68
    Activations Density 0.186%

    No Known Activations