© 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. 31225
    Prev
    Next
    INDEX
    Explanations

    key terms related to business and organizational dynamics

    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
    511
    +0.12
    0.6%
    765
    +0.12
    0.5%
    53
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.15
    365
    +0.12
    0.01
    220
    +0.11
    0.07
    Negative Logits
     Version
    -0.70
     ende
    -0.67
     version
    -0.66
    eatures
    -0.65
    entimes
    -0.65
    chel
    -0.64
    ittees
    -0.64
     portion
    -0.63
    Versions
    -0.61
    Of
    -0.60
    POSITIVE LOGITS
     goodness
    0.78
     intrigue
    0.64
    votes
    0.63
     interconnected
    0.61
     proportions
    0.60
     goodies
    0.60
    bable
    0.59
     excellence
    0.58
     hormones
    0.57
     fame
    0.57
    Activations Density 2.225%

    No Known Activations