© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5664
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the need for action or assistance

    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
    194
    +0.11
    0.5%
    264
    +0.11
    0.5%
    735
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.10
    718
    +0.11
    0.10
    665
    +0.10
    0.09
    Negative Logits
    Browser
    -0.70
     Became
    -0.68
    atility
    -0.66
    Hig
    -0.64
    hig
    -0.64
     Retrieved
    -0.64
    BG
    -0.62
    rue
    -0.62
    GMT
    -0.61
    EXP
    -0.61
    POSITIVE LOGITS
     superv
    1.17
     oversee
    1.07
     shepherd
    0.96
     handle
    0.90
     whom
    0.89
     reins
    0.85
     guiding
    0.85
     overseeing
    0.84
     babys
    0.82
     guide
    0.82
    Activations Density 0.619%

    No Known Activations