© 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. 30536
    Prev
    Next
    INDEX
    Explanations

    structured data or programming concepts

    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
    373
    +0.12
    0.5%
    79
    +0.11
    0.5%
    512
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.12
    0.01
    227
    +0.11
    0.00
    562
    +0.09
    0.01
    Negative Logits
    senal
    -0.73
     GM
    -0.66
     mold
    -0.65
     successes
    -0.63
     mould
    -0.62
     womb
    -0.62
     VW
    -0.61
     revolving
    -0.61
    ndra
    -0.61
     inertia
    -0.60
    POSITIVE LOGITS
    Merit
    0.94
    rina
    0.87
    leans
    0.83
    Lear
    0.76
    eat
    0.76
    yr
    0.75
    reads
    0.75
    unny
    0.75
    lean
    0.74
    rik
    0.72
    Activations Density 0.035%

    No Known Activations