© 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. 30031
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in."

    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
    469
    +0.15
    0.7%
    750
    +0.12
    0.6%
    123
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.15
    0.09
    469
    +0.12
    0.08
    323
    +0.11
    0.05
    Negative Logits
    ãĤ¹
    -0.68
    Ĵ
    -0.64
    ·
    -0.64
    ifa
    -0.62
    ãĥĪ
    -0.61
    Ŀ
    -0.60
    ļ
    -0.60
    ŀ
    -0.60
    STER
    -0.59
    lain
    -0.59
    POSITIVE LOGITS
    wards
    1.04
     unison
    1.02
     front
    0.91
    humane
    0.89
    escap
    0.88
    between
    0.87
     conjunction
    0.86
     tandem
    0.86
     vain
    0.86
     vitro
    0.83
    Activations Density 0.626%

    No Known Activations