© 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. 30706
    Prev
    Next
    INDEX
    Explanations

    the word "while" in various contexts

    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
    476
    +0.11
    0.5%
    172
    +0.10
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.11
    0.04
    738
    +0.10
    0.04
    14
    +0.10
    0.03
    Negative Logits
    ahime
    -0.96
    iotic
    -0.85
    hack
    -0.82
    kr
    -0.81
    endar
    -0.79
    illet
    -0.79
    krit
    -0.78
    dayName
    -0.78
    iggurat
    -0.77
    ipolar
    -0.76
    POSITIVE LOGITS
     retaining
    1.22
     simultaneously
    1.21
     maintaining
    1.20
     others
    1.19
     ignoring
    1.01
     preserving
    0.99
     also
    0.94
     awaiting
    0.93
     acknowledging
    0.93
     keeping
    0.92
    Activations Density 0.266%

    No Known Activations