© 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. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3169
    Prev
    Next
    INDEX
    Explanations

    structured data or references to technical or mathematical subjects

    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
    481
    +0.16
    0.8%
    497
    +0.15
    0.7%
    756
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.16
    0.05
    386
    +0.15
    0.06
    539
    +0.10
    0.06
    Negative Logits
    ér
    -0.79
    plot
    -0.63
    etheless
    -0.61
     downed
    -0.58
    shape
    -0.56
     nodded
    -0.56
    iren
    -0.56
    minist
    -0.55
    ciples
    -0.55
     yuan
    -0.55
    POSITIVE LOGITS
    çīĪ
    0.76
    ãĤ¢ãĥ«
    0.73
    ãĥĨ
    0.69
    )</
    0.65
    ãĥĥãĥĪ
    0.65
     Townsend
    0.64
    ãĥIJ
    0.64
    ãĥīãĥ©
    0.63
    å§«
    0.63
    interstitial
    0.63
    Activations Density 1.516%

    No Known Activations