© 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. 32150
    Prev
    Next
    INDEX
    Explanations

    phrases indicating present states or actions

    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
    314
    +0.11
    0.5%
    723
    +0.10
    0.5%
    108
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.11
    0.14
    566
    +0.10
    0.11
    55
    +0.09
    0.14
    Negative Logits
     coerc
    -0.65
    yip
    -0.63
     Citiz
    -0.61
     beck
    -0.61
    zsche
    -0.59
     mosquitoes
    -0.57
     Manifest
    -0.56
    natureconservancy
    -0.56
     Labs
    -0.56
     Else
    -0.55
    POSITIVE LOGITS
     now
    1.29
     hindsight
    1.26
     remembered
    1.13
     recollection
    1.11
     regret
    1.07
     regrets
    1.05
    now
    1.04
     remember
    1.03
     retrospect
    1.00
     regretted
    0.97
    Activations Density 2.701%

    No Known Activations