© 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. 26571
    Prev
    Next
    INDEX
    Explanations

    elements related to documents, such as dates, responses, and email content

    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
    314
    +0.11
    0.5%
    391
    +0.09
    0.4%
    735
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.11
    0.05
    314
    +0.09
    -0.02
    267
    +0.09
    0.08
    Negative Logits
     contextual
    -0.66
     envision
    -0.64
     elev
    -0.63
     glim
    -0.62
    )].
    -0.61
     adversaries
    -0.61
     medicines
    -0.61
     overlap
    -0.60
     filmmakers
    -0.60
    entimes
    -0.60
    POSITIVE LOGITS
     Reply
    1.55
     Quote
    1.51
     Posted
    1.47
    Joined
    1.35
    Posts
    1.31
     Posts
    1.27
    Reply
    1.21
     Originally
    1.20
     Thanks
    1.17
    Hi
    1.15
    Activations Density 1.578%

    No Known Activations