© 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. 4142
    Prev
    Next
    INDEX
    Explanations

    terms related to searching or detection

    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
    263
    +0.11
    0.5%
    761
    +0.11
    0.5%
    444
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.11
    0.03
    761
    +0.11
    0.02
    444
    +0.10
    0.02
    Negative Logits
    ãĥĺ
    -0.92
    ãĥķãĤ©
    -0.90
    EMENT
    -0.86
     srfAttach
    -0.80
    ASED
    -0.80
    ãĥ¼ãĥĨ
    -0.79
    ãĥ¼ãĥĨãĤ£
    -0.79
    GBT
    -0.78
    irez
    -0.78
    ãĤ¼ãĤ¦ãĤ¹
    -0.74
    POSITIVE LOGITS
    mouth
    0.87
    achus
    0.85
    phrine
    0.84
     nose
    0.75
     vom
    0.74
     gigg
    0.74
    iba
    0.71
     cider
    0.71
     clinically
    0.70
     hyster
    0.70
    Activations Density 0.138%

    No Known Activations