© 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. 28075
    Prev
    Next
    INDEX
    Explanations

    numerical data and dates related to events or records

    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
    +0.14
    0.6%
    373
    +0.13
    0.6%
    107
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.14
    0.02
    107
    +0.13
    0.02
    695
    +0.12
    0.02
    Negative Logits
     migrated
    -0.73
     hostage
    -0.71
    terday
    -0.69
     plunge
    -0.68
     Gutenberg
    -0.67
     sooner
    -0.66
     firsthand
    -0.65
     360
    -0.64
     Hutchinson
    -0.63
     Mara
    -0.62
    POSITIVE LOGITS
    2016
    1.13
    2015
    1.10
    2017
    1.10
    2014
    1.04
    2019
    1.00
    âĸĪâĸĪ
    0.97
    2011
    0.96
    08
    0.96
    2018
    0.96
    2013
    0.96
    Activations Density 0.067%

    No Known Activations