© 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. 32421
    Prev
    Next
    INDEX
    Explanations

    comparative terms related to costs and savings

    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
    459
    +0.14
    0.6%
    408
    +0.11
    0.5%
    379
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.14
    0.05
    95
    +0.11
    0.04
    351
    +0.10
    0.04
    Negative Logits
    ©¶æ
    -0.87
    ij士
    -0.84
    ²¾
    -0.74
    successful
    -0.74
    ĪĴ
    -0.70
    sych
    -0.70
     Cosponsors
    -0.70
    lectic
    -0.70
    errors
    -0.70
    ourning
    -0.69
    POSITIVE LOGITS
     money
    1.17
     per
    0.98
     attention
    0.91
     ($
    0.81
     apiece
    0.80
     dollars
    0.79
     bucks
    0.78
     cash
    0.78
     electricity
    0.75
     income
    0.75
    Activations Density 0.408%

    No Known Activations