© 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. 26924
    Prev
    Next
    INDEX
    Explanations

    terms related to health and economic impacts

    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
    278
    +0.10
    0.4%
    359
    +0.09
    0.4%
    43
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.14
    575
    +0.09
    0.11
    51
    +0.09
    0.10
    Negative Logits
    DragonMagazine
    -0.74
     invented
    -0.67
     Canaver
    -0.61
     greet
    -0.60
     pioneered
    -0.59
     inserted
    -0.58
     Mandarin
    -0.58
     unaccompanied
    -0.58
     mutated
    -0.57
    oresc
    -0.57
    POSITIVE LOGITS
     negatively
    1.17
     morale
    1.12
     overall
    1.00
     competitiveness
    1.00
     adversely
    1.00
     tremendously
    0.98
     immensely
    0.98
     stability
    0.97
     prospects
    0.96
     productivity
    0.95
    Activations Density 1.777%

    No Known Activations