© 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. 32723
    Prev
    Next
    INDEX
    Explanations

    instances of the character "i" in various contexts

    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
    385
    +0.12
    0.6%
    274
    +0.10
    0.5%
    711
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    0.00
    284
    +0.10
    0.02
    228
    +0.10
    0.02
    Negative Logits
    ters
    -0.71
    humans
    -0.70
    ricular
    -0.66
    aminer
    -0.65
    rette
    -0.64
    fits
    -0.63
    verts
    -0.62
    bler
    -0.61
    teen
    -0.60
    blers
    -0.60
    POSITIVE LOGITS
    ãģĨ
    1.20
    å®
    0.97
    åĮ
    0.94
    ãģ£
    0.91
    ا
    0.90
    ãĤ£
    0.89
    èĢħ
    0.84
    åŃ
    0.83
    е
    0.82
    å¦
    0.81
    Activations Density 0.150%

    No Known Activations