© 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. 5193
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'n'

    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
    478
    +0.12
    0.6%
    159
    +0.10
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.05
    364
    +0.10
    0.05
    336
    +0.10
    0.04
    Negative Logits
     Lumpur
    -0.76
     Lama
    -0.74
     Ferdinand
    -0.67
     Doctors
    -0.64
    NEY
    -0.63
     Drain
    -0.62
     Vaj
    -0.61
     boss
    -0.61
     EntityItem
    -0.59
     Coun
    -0.59
    POSITIVE LOGITS
    itty
    0.93
    onda
    0.91
    umin
    0.89
    apo
    0.88
    ano
    0.82
    anny
    0.81
    urs
    0.79
    Drive
    0.78
    vidia
    0.78
    idem
    0.78
    Activations Density 0.144%

    No Known Activations