© 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. 28813
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases that indicate relationships or connections between entities

    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
    393
    +0.11
    0.5%
    597
    +0.10
    0.5%
    605
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.11
    0.01
    211
    +0.10
    0.01
    549
    +0.09
    0.01
    Negative Logits
    icum
    -0.66
    soType
    -0.59
    atorium
    -0.59
     pilgr
    -0.58
    apego
    -0.57
     pardon
    -0.57
    aji
    -0.57
     pronouns
    -0.57
    onym
    -0.56
     Klu
    -0.56
    POSITIVE LOGITS
    icial
    0.86
     1932
    0.76
    course
    0.74
     580
    0.73
     31
    0.73
     32
    0.71
     22
    0.71
     38
    0.71
     46
    0.70
     27
    0.70
    Activations Density 0.083%

    No Known Activations