© 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. 3416
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to politics and governmental roles

    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
    71
    +0.17
    0.8%
    669
    +0.10
    0.5%
    270
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    589
    +0.17
    0.01
    284
    +0.10
    0.01
    129
    +0.10
    0.01
    Negative Logits
    xus
    -0.76
     Watkins
    -0.63
     pus
    -0.61
    rency
    -0.60
    wise
    -0.58
    eligible
    -0.58
     veins
    -0.57
     Dull
    -0.57
    ĸļ
    -0.56
    orius
    -0.56
    POSITIVE LOGITS
    owship
    0.89
    FTWARE
    0.67
    ailability
    0.64
    Brave
    0.63
    âĹ¼
    0.62
    izations
    0.61
    ||
    0.60
     Romance
    0.60
    QL
    0.60
    Ö
    0.59
    Activations Density 0.007%

    No Known Activations