© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5818
    Prev
    Next
    INDEX
    Explanations

    references to specific video game titles or versions

    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
    314
    +0.12
    0.6%
    46
    +0.11
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    -0.03
    493
    +0.11
    0.04
    409
    +0.11
    0.04
    Negative Logits
     Juda
    -0.63
     Dish
    -0.61
     Cart
    -0.60
     Crab
    -0.59
     resear
    -0.58
     Pharaoh
    -0.57
    akia
    -0.56
    rawdownloadcloneembedreportprint
    -0.55
     Scully
    -0.55
     Dre
    -0.55
    POSITIVE LOGITS
    interstitial
    0.96
    qq
    0.75
    è£ħ
    0.73
    BuyableInstoreAndOnline
    0.72
    ä¸Ĭ
    0.69
    iannopoulos
    0.66
    ãĥį
    0.66
    geries
    0.64
    ä¸Ń
    0.63
    ateful
    0.62
    Activations Density 1.636%

    No Known Activations