© 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. 10-RES_POST_32K-OAI
    11. 32754
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to laying out plans or proposals

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    25
    +0.11
    0.5%
    724
    +0.11
    0.5%
    72
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.05
    458
    +0.11
    0.04
    724
    +0.10
    0.05
    Negative Logits
     Unsure
    -0.71
    blers
    -0.69
     luck
    -0.64
    oso
    -0.59
    tes
    -0.57
    antam
    -0.56
     bumped
    -0.55
    CHA
    -0.55
     Introduced
    -0.55
    bling
    -0.55
    POSITIVE LOGITS
     principles
    1.00
     plans
    0.93
     objectives
    0.92
     clearly
    0.89
     goals
    0.88
     outlines
    0.88
     guidelines
    0.88
     plainly
    0.86
     criteria
    0.85
     requirements
    0.82
    Activations Density 0.422%

    No Known Activations