© 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 EvalsExportsAPI 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. 30503
    Prev
    Next
    INDEX
    Explanations

    quotes and statements related to tragedies and apologies

    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
    629
    +0.12
    0.5%
    741
    +0.10
    0.5%
    187
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.12
    0.09
    145
    +0.10
    0.06
    107
    +0.09
    0.06
    Negative Logits
     richest
    -0.74
     lure
    -0.71
     quir
    -0.71
    yip
    -0.69
    hack
    -0.69
     nodd
    -0.68
     knack
    -0.68
     crammed
    -0.66
     richer
    -0.66
     whiff
    -0.66
    POSITIVE LOGITS
    Due
    0.82
    Statement
    0.80
     Statements
    0.79
    Following
    0.79
    Effective
    0.77
     regrett
    0.76
    ADA
    0.76
    orously
    0.75
     Accordingly
    0.75
    âĢİ
    0.73
    Activations Density 0.547%

    No Known Activations