© 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. 32646
    Prev
    Next
    INDEX
    Explanations

    references to legislative acts and their details

    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
    466
    +0.13
    0.6%
    547
    +0.11
    0.5%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.13
    0.07
    253
    +0.11
    0.07
    426
    +0.10
    0.05
    Negative Logits
    entimes
    -0.64
    payers
    -0.63
     dunno
    -0.61
    engers
    -0.60
    facts
    -0.60
    ratulations
    -0.58
     demos
    -0.57
    tur
    -0.57
     Machina
    -0.56
    Unity
    -0.55
    POSITIVE LOGITS
     redesign
    1.00
     amended
    0.99
     added
    0.96
     substituted
    0.95
    Effective
    0.92
     inserted
    0.88
    Added
    0.87
    Cod
    0.86
     repealed
    0.85
     deleted
    0.84
    Activations Density 0.862%

    No Known Activations