© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31417
    Prev
    Next
    INDEX
    Explanations

    references to advertising or commercial influences

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    693
    +0.10
    0.4%
    325
    +0.09
    0.4%
    599
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.10
    0.02
    314
    +0.09
    -0.01
    260
    +0.08
    0.02
    Negative Logits
    etsk
    -0.74
    urus
    -0.70
     Ark
    -0.70
    erton
    -0.68
    etter
    -0.67
    etting
    -0.66
     Paddock
    -0.64
    istor
    -0.61
     Bulgar
    -0.61
    essler
    -0.61
    POSITIVE LOGITS
    000
    0.93
    4000
    0.89
    500
    0.78
    5000
    0.77
    1800
    0.74
    6000
    0.73
    1001
    0.73
    0000
    0.73
    2000
    0.71
    1000
    0.71
    Activations Density 0.084%

    No Known Activations