© 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. 4099
    Prev
    Next
    INDEX
    Explanations

    the phrase "for" followed by various expressions, indicating conditions or requests

    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
    314
    +0.16
    0.7%
    222
    +0.10
    0.5%
    276
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.16
    0.05
    161
    +0.10
    0.04
    163
    +0.10
    0.04
    Negative Logits
    pired
    -0.67
    oos
    -0.63
    tain
    -0.63
    displayText
    -0.62
    waters
    -0.62
     deceive
    -0.61
     Method
    -0.61
    soever
    -0.61
    Myth
    -0.61
    packing
    -0.61
    POSITIVE LOGITS
     earthqu
    0.72
    apses
    0.66
    ellar
    0.65
    illary
    0.64
     âĵĺ
    0.64
     laps
    0.64
    dylib
    0.64
     rebounds
    0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.63
     reasons
    0.63
    Activations Density 0.544%

    No Known Activations