© 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. 8-RES_POST_32K-OAI
    11. 6496
    Prev
    Next
    INDEX
    Explanations

    instances of specific characters or symbols, particularly those associated with Arabic text

    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
    728
    +0.10
    0.5%
    372
    +0.10
    0.5%
    385
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.10
    0.01
    73
    +0.10
    0.01
    314
    +0.10
    -0.00
    Negative Logits
    dor
    -0.87
    nell
    -0.80
    abase
    -0.79
    aic
    -0.78
    ean
    -0.77
    inates
    -0.75
    ional
    -0.74
    aminer
    -0.74
    atile
    -0.73
    kinson
    -0.73
    POSITIVE LOGITS
    Í
    0.95
    ãģĹ
    0.85
    æ³
    0.84
    ãĤĭ
    0.82
    æľ
    0.82
    æµ
    0.81
    å¸
    0.80
    ãĤ´ãĥ³
    0.77
    Ùĩ
    0.77
    ãĥ³ãĤ¸
    0.76
    Activations Density 0.039%

    No Known Activations