© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3766
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate collective action or shared experiences

    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
    509
    +0.12
    0.5%
    214
    +0.11
    0.5%
    558
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.12
    0.04
    509
    +0.11
    0.04
    598
    +0.09
    0.03
    Negative Logits
    ologists
    -0.68
     Ladies
    -0.68
    enegger
    -0.67
    OLOGY
    -0.66
    ological
    -0.66
     Journals
    -0.66
    boxing
    -0.64
    ologic
    -0.63
     Maze
    -0.62
     Robotics
    -0.62
    POSITIVE LOGITS
    abwe
    0.74
    azard
    0.69
     withd
    0.68
    upon
    0.68
     compr
    0.67
     lia
    0.66
     cooperate
    0.65
     sidx
    0.65
    zers
    0.64
    MpServer
    0.64
    Activations Density 0.119%

    No Known Activations