© 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. 29665
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate comments or responses from individuals or organizations

    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
    121
    +0.12
    0.5%
    279
    +0.11
    0.5%
    378
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.12
    0.22
    640
    +0.11
    0.16
    145
    +0.11
    0.15
    Negative Logits
    ebted
    -0.68
     ageing
    -0.68
    urion
    -0.66
     disadvantage
    -0.65
     disadvantages
    -0.65
     curing
    -0.64
    _-_
    -0.63
    ometimes
    -0.63
     staple
    -0.62
    often
    -0.61
    POSITIVE LOGITS
     spokes
    0.99
     emailed
    0.96
     spokesperson
    0.95
     spokeswoman
    0.91
     spokesman
    0.82
    Update
    0.81
    Statement
    0.80
     TMZ
    0.77
    UPDATE
    0.76
     Neither
    0.76
    Activations Density 1.583%

    No Known Activations