© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 7715
    Prev
    Next
    INDEX
    Explanations

    phrases that express speech or communication, particularly focusing on declarations and prayers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    25
    +0.12
    0.5%
    449
    +0.12
    0.5%
    282
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.12
    0.05
    282
    +0.12
    0.07
    191
    +0.10
    0.02
    Negative Logits
     Folder
    -0.68
    rontal
    -0.66
     encl
    -0.66
     Flickr
    -0.65
    Mania
    -0.64
     Eag
    -0.64
     replication
    -0.61
    mentation
    -0.60
     Byrne
    -0.60
     photograp
    -0.58
    POSITIVE LOGITS
     aloud
    1.15
     words
    1.01
     truths
    0.95
     corrid
    0.90
     mantra
    0.88
     phrases
    0.88
    word
    0.87
     prayers
    0.87
     goodbye
    0.87
     slogans
    0.87
    Activations Density 1.523%

    No Known Activations