© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 32176
    Prev
    Next
    INDEX
    Explanations

    terms related to rigor and strictness in various contexts

    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
    326
    +0.12
    0.6%
    291
    +0.11
    0.5%
    526
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.12
    0.00
    326
    +0.11
    0.02
    291
    +0.11
    0.01
    Negative Logits
    terson
    -0.67
    theless
    -0.65
     Franch
    -0.64
     wart
    -0.61
     Bie
    -0.60
    letters
    -0.59
     Peninsula
    -0.58
     Sacrament
    -0.58
     Hots
    -0.58
     VIDEOS
    -0.57
    POSITIVE LOGITS
    orously
    1.66
    idity
    1.40
    ged
    1.23
    ging
    1.13
    gers
    1.11
    yrinth
    1.09
    ger
    1.07
    amar
    1.06
    gins
    1.03
    orous
    1.01
    Activations Density 0.120%

    No Known Activations