© 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. 29082
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities, particularly names related to media and organizations

    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
    314
    +0.13
    0.6%
    684
    +0.12
    0.5%
    398
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.13
    0.17
    23
    +0.12
    0.15
    103
    +0.11
    0.13
    Negative Logits
    ãĤ©
    -0.81
     blur
    -0.67
     Dar
    -0.66
    reenshot
    -0.66
    */(
    -0.64
    oother
    -0.62
    aturated
    -0.61
     Buk
    -0.59
    taboola
    -0.59
     dos
    -0.59
    POSITIVE LOGITS
    Chem
    1.02
    Games
    0.94
    Fa
    0.93
    elligence
    0.92
    swers
    0.92
    Six
    0.89
    Gold
    0.89
    Ge
    0.88
    Sea
    0.88
    Plan
    0.87
    Activations Density 1.867%

    No Known Activations