© 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. 31132
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "so" used for emphasis

    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
    464
    +0.09
    0.4%
    494
    +0.09
    0.4%
    513
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.09
    0.06
    55
    +0.09
    0.05
    11
    +0.09
    0.04
    Negative Logits
     Flavoring
    -0.82
    llor
    -0.72
     VIDEOS
    -0.66
     âĵĺ
    -0.63
     Album
    -0.62
     Slave
    -0.61
     Noct
    -0.61
     clears
    -0.60
     Residents
    -0.59
    ibling
    -0.59
    POSITIVE LOGITS
     ingrained
    0.98
     overpower
    0.85
     entrenched
    0.84
     insepar
    0.82
     overwhelmingly
    0.79
     riddled
    0.79
     irresistible
    0.77
     intertwined
    0.76
    greg
    0.76
     pervasive
    0.76
    Activations Density 0.211%

    No Known Activations