© 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. 29333
    Prev
    Next
    INDEX
    Explanations

    possessive forms and references to ownership

    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%
    167
    +0.14
    0.6%
    393
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.07
    167
    +0.14
    0.02
    646
    +0.13
    0.04
    Negative Logits
    perse
    -0.73
    vous
    -0.73
    iencies
    -0.71
     Canaver
    -0.70
    ilts
    -0.70
    ypes
    -0.69
     [+
    -0.69
    apo
    -0.69
     whereby
    -0.68
    ĸļ
    -0.68
    POSITIVE LOGITS
     own
    1.48
     favorite
    1.28
     favourite
    1.21
     opponent
    1.21
     spouse
    1.07
     adversary
    1.03
     nearest
    1.00
     entire
    0.99
     beloved
    0.98
     girlfriend
    0.94
    Activations Density 0.389%

    No Known Activations