© 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. 30585
    Prev
    Next
    INDEX
    Explanations

    the word "because" in various contexts, indicating reasons or justifications

    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
    699
    +0.10
    0.5%
    408
    +0.10
    0.4%
    218
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.10
    0.04
    218
    +0.10
    0.04
    155
    +0.10
    0.05
    Negative Logits
    unless
    -0.76
    puter
    -0.68
    depending
    -0.66
     unless
    -0.65
    ãĥ¼ãĥ³
    -0.62
     apart
    -0.62
    mediately
    -0.61
    elta
    -0.60
    together
    -0.60
    ilet
    -0.60
    POSITIVE LOGITS
     someone
    0.90
     somebody
    0.85
     she
    0.79
     he
    0.76
     they
    0.72
    pires
    0.72
     policymakers
    0.68
    fy
    0.67
     we
    0.64
     THEY
    0.61
    Activations Density 0.211%

    No Known Activations