© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29647
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "half."

    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
    314
    +0.14
    0.7%
    298
    +0.12
    0.5%
    102
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.14
    0.03
    333
    +0.12
    0.02
    102
    +0.11
    0.02
    Negative Logits
     Zup
    -0.71
     QC
    -0.66
     superior
    -0.64
     Ples
    -0.64
     DRAG
    -0.64
     Miko
    -0.62
     subscript
    -0.62
     proport
    -0.61
     inflamm
    -0.61
     prolifer
    -0.60
    POSITIVE LOGITS
    dozen
    1.56
    assed
    1.32
    hour
    1.25
    eat
    1.19
    assing
    1.14
    truth
    1.14
    century
    1.08
    heartedly
    1.08
    hearted
    1.08
    empty
    1.08
    Activations Density 0.105%

    No Known Activations