© 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. 10-RES_POST_32K-OAI
    11. 29942
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ny" or similar variations, likely related to proper nouns or place names

    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
    291
    +0.11
    0.5%
    17
    +0.11
    0.5%
    20
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.05
    232
    +0.11
    0.05
    291
    +0.09
    0.04
    Negative Logits
    IBLE
    -0.86
    izable
    -0.72
    isable
    -0.71
    itarian
    -0.70
    aciously
    -0.68
     elig
    -0.68
    etic
    -0.66
    acity
    -0.65
    itative
    -0.65
    ITY
    -0.65
    POSITIVE LOGITS
    dd
    1.06
    ng
    1.02
    mph
    0.99
    eah
    0.99
    lene
    0.99
    ea
    0.98
    tsky
    0.97
    nn
    0.95
    yy
    0.95
    outube
    0.91
    Activations Density 0.670%

    No Known Activations