© 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. 7654
    Prev
    Next
    INDEX
    Explanations

    references to social media activities, particularly tweeting and retweeting

    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
    706
    +0.11
    0.5%
    13
    +0.10
    0.4%
    294
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.11
    0.04
    13
    +0.10
    0.04
    23
    +0.10
    0.04
    Negative Logits
    sbm
    -0.68
     clitor
    -0.65
    cised
    -0.65
    vantage
    -0.64
    cester
    -0.62
     circumcision
    -0.61
    ajor
    -0.59
    undai
    -0.59
     Chr
    -0.58
     Kits
    -0.58
    POSITIVE LOGITS
    storms
    1.11
    storm
    0.96
    deck
    0.91
     hashtag
    0.88
     hasht
    0.83
    @@@@@@@@
    0.82
     feeds
    0.79
     "@
    0.78
    Tweet
    0.76
    weet
    0.76
    Activations Density 0.087%

    No Known Activations