© 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. 8974
    Prev
    Next
    INDEX
    Explanations

    references to official documents or reports related to legal and governmental matters

    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
    373
    +0.15
    0.7%
    308
    +0.12
    0.6%
    731
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.15
    0.11
    540
    +0.12
    0.10
    386
    +0.10
    0.08
    Negative Logits
    uxe
    -0.78
    姫
    -0.72
    oko
    -0.65
    rex
    -0.64
    ometric
    -0.62
    ranch
    -0.61
    LP
    -0.61
    itely
    -0.60
    bial
    -0.57
    unts
    -0.55
    POSITIVE LOGITS
     announcing
    0.79
     regarding
    0.78
     detailing
    0.74
     titled
    0.73
     touting
    0.73
     referencing
    0.73
     pertaining
    0.72
     concerning
    0.71
     involving
    0.71
     depicting
    0.69
    Activations Density 1.057%

    No Known Activations