© 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. 8-RES_POST_32K-OAI
    6. 4490
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential actions, assumptions, and contemplations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    429
    +0.14
    0.6%
    439
    +0.11
    0.5%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.14
    0.04
    429
    +0.11
    0.03
    551
    +0.09
    0.03
    Negative Logits
    IDs
    -0.69
    ORS
    -0.65
     Stain
    -0.64
    CRE
    -0.63
    Hide
    -0.63
    ãĤµ
    -0.63
    Beta
    -0.62
     Beet
    -0.62
    ONEY
    -0.62
    quickShipAvailable
    -0.61
    POSITIVE LOGITS
     oneself
    1.00
    £ı
    0.88
    lihood
    0.80
    elf
    0.79
    pheus
    0.76
     wishing
    0.72
     speculate
    0.71
    chal
    0.71
    hat
    0.70
    imensional
    0.69
    Activations Density 0.437%

    No Known Activations