© 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. 30708
    Prev
    Next
    INDEX
    Explanations

    references to evidence-based medicine and its critiques

    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
    160
    +0.10
    0.5%
    756
    +0.10
    0.5%
    291
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.10
    0.07
    314
    +0.10
    0.01
    160
    +0.10
    0.06
    Negative Logits
     Solitaire
    -0.66
     ILCS
    -0.66
     braces
    -0.65
     pigeon
    -0.64
     miss
    -0.62
     wait
    -0.62
     overcrowd
    -0.62
     waiter
    -0.62
     straw
    -0.62
     rentals
    -0.60
    POSITIVE LOGITS
    oriented
    1.25
    driven
    1.23
    based
    1.22
    fiction
    1.17
    laden
    1.11
    defined
    1.02
    filled
    1.01
    focused
    0.99
    designed
    0.97
    seeking
    0.97
    Activations Density 0.450%

    No Known Activations