© 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. 4436
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate importance or emphasis

    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
    55
    +0.10
    0.4%
    276
    +0.09
    0.4%
    525
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.10
    0.05
    168
    +0.09
    0.04
    621
    +0.09
    0.04
    Negative Logits
    iken
    -0.69
    omy
    -0.66
    ake
    -0.61
     diagram
    -0.60
    ahime
    -0.59
    fly
    -0.58
    iquid
    -0.58
    oki
    -0.56
     Sale
    -0.56
     Motion
    -0.56
    POSITIVE LOGITS
    ernels
    0.78
     equally
    0.77
    sites
    0.75
    yss
    0.72
    romeda
    0.71
    umenthal
    0.68
     reinforcements
    0.68
    iller
    0.66
    abouts
    0.65
    same
    0.65
    Activations Density 0.949%

    No Known Activations