© 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. 29845
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "art" in various forms

    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
    523
    +0.10
    0.5%
    377
    +0.10
    0.5%
    26
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.10
    -0.00
    659
    +0.10
    0.02
    232
    +0.10
    0.02
    Negative Logits
     overse
    -0.67
     safety
    -0.63
    OPLE
    -0.62
    âĵĺ
    -0.61
     safely
    -0.60
     lists
    -0.59
     detachment
    -0.57
     Empires
    -0.57
    士
    -0.56
     yes
    -0.55
    POSITIVE LOGITS
    ificial
    1.24
    isan
    1.13
    icles
    1.13
    ifacts
    1.13
    ifact
    1.11
    istic
    1.08
    ific
    1.07
    illery
    0.99
    ists
    0.95
    osis
    0.92
    Activations Density 0.197%

    No Known Activations