© 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. 28833
    Prev
    Next
    INDEX
    Explanations

    instances of numeric or date formats

    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
    442
    +0.18
    0.8%
    107
    +0.12
    0.6%
    430
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.18
    0.02
    430
    +0.12
    0.02
    107
    +0.12
    0.02
    Negative Logits
     Pitch
    -0.77
    etheless
    -0.74
     Tre
    -0.72
     Creed
    -0.72
     reversible
    -0.71
     points
    -0.71
     rul
    -0.70
     brim
    -0.70
     posters
    -0.68
     sided
    -0.68
    POSITIVE LOGITS
    2018
    1.73
    2017
    1.68
    2019
    1.67
    2015
    1.56
    2020
    1.53
    2016
    1.50
    2009
    1.44
    2014
    1.42
    2013
    1.41
    2012
    1.41
    Activations Density 0.076%

    No Known Activations