© 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. 26586
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical values or identifiers

    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
    431
    +0.12
    0.5%
    606
    +0.11
    0.5%
    689
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    643
    +0.12
    0.00
    85
    +0.11
    0.01
    588
    +0.10
    0.01
    Negative Logits
    teness
    -0.86
    Advertisements
    -0.79
    anguage
    -0.74
    Score
    -0.74
    YES
    -0.70
    *:
    -0.69
    iqueness
    -0.68
    bugs
    -0.68
    nces
    -0.67
    omnia
    -0.67
    POSITIVE LOGITS
     guiName
    1.66
     guiIcon
    1.08
     guiActiveUnfocused
    1.06
     externalToEVAOnly
    1.01
     guiActive
    0.96
     Node
    0.75
     Generator
    0.75
     category
    0.75
     }
    0.75
     Controller
    0.74
    Activations Density 0.044%

    No Known Activations