© 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. 29030
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pl" or variations of it, potentially indicating a focus on specific terms or acronyms related to structured environments

    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
    756
    +0.10
    0.5%
    682
    +0.10
    0.5%
    450
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.10
    -0.01
    232
    +0.10
    0.04
    289
    +0.10
    0.01
    Negative Logits
    rament
    -0.82
    auga
    -0.80
    pring
    -0.74
     cloves
    -0.72
    STE
    -0.72
    tale
    -0.72
    rity
    -0.72
    busters
    -0.69
    tones
    -0.68
    uka
    -0.66
    POSITIVE LOGITS
    acement
    0.99
    acements
    0.85
    ensation
    0.70
    iter
    0.69
    iability
    0.69
    YING
    0.68
    icit
    0.68
    ensable
    0.66
    itable
    0.65
     Responsibility
    0.65
    Activations Density 0.327%

    No Known Activations