© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 4400
    Prev
    Next
    INDEX
    Explanations

    references to significant amounts of money or numeric data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.3.hook_attn_out
    Hook Layer
    3
    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
    497
    +0.19
    0.9%
    71
    +0.13
    0.6%
    109
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.19
    0.00
    182
    +0.13
    0.01
    199
    +0.11
    0.01
    Negative Logits
    heit
    -0.82
     Nanto
    -0.81
     Norn
    -0.74
     newcomers
    -0.66
    rians
    -0.66
    Reference
    -0.65
    ÄŁ
    -0.65
    Reviewed
    -0.64
    ité
    -0.64
     âĵĺ
    -0.64
    POSITIVE LOGITS
    aez
    0.73
    chieve
    0.72
    Ļ
    0.68
    ģ«
    0.67
    interstitial
    0.65
    Ĥİ
    0.65
    Morgan
    0.64
    ļ
    0.62
    Ŀ
    0.61
    silver
    0.59
    Activations Density 0.015%

    No Known Activations