© 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. 30073
    Prev
    Next
    INDEX
    Explanations

    instances of the word "according."

    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
    679
    +0.11
    0.5%
    285
    +0.10
    0.4%
    661
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.11
    0.05
    130
    +0.10
    0.04
    514
    +0.10
    0.04
    Negative Logits
    ĸļ
    -0.79
    neys
    -0.71
    ensen
    -0.70
    crow
    -0.64
    disk
    -0.63
    uckland
    -0.62
     +++
    -0.62
    ãĥĵ
    -0.61
     wedge
    -0.60
    tsky
    -0.60
    POSITIVE LOGITS
    ly
    1.08
    lly
    0.86
    LY
    0.85
    liest
    0.74
    liness
    0.71
    edly
    0.70
    eous
    0.70
    fully
    0.66
    ety
    0.65
    ously
    0.64
    Activations Density 0.299%

    No Known Activations