© 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. 28845
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership or possession

    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
    362
    +0.15
    0.7%
    669
    +0.14
    0.6%
    393
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.15
    0.09
    362
    +0.14
    0.10
    608
    +0.13
    0.09
    Negative Logits
    >(
    -0.93
    wcsstore
    -0.83
    BILITIES
    -0.82
    /"
    -0.79
    igun
    -0.72
    BuyableInstoreAndOnline
    -0.72
    ................................................................
    -0.72
    bernatorial
    -0.71
    fml
    -0.69
    aukee
    -0.69
    POSITIVE LOGITS
     others
    1.15
     those
    0.99
     passers
    0.97
     strangers
    0.97
     whoever
    0.92
     individuals
    0.91
     millions
    0.90
     onlook
    0.87
     Others
    0.85
     mankind
    0.85
    Activations Density 0.562%

    No Known Activations