© 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. 4433
    Prev
    Next
    INDEX
    Explanations

    references to long-term concepts or conditions

    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
    420
    +0.24
    1.1%
    436
    +0.13
    0.6%
    395
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.24
    0.01
    459
    +0.13
    0.01
    460
    +0.10
    0.03
    Negative Logits
     agre
    -0.71
     overtake
    -0.71
    iannopoulos
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
     earthqu
    -0.66
    okane
    -0.63
    daq
    -0.62
     laun
    -0.62
     injure
    -0.62
    OTUS
    -0.61
    POSITIVE LOGITS
     reflections
    0.67
     Ley
    0.63
    binding
    0.62
    Bio
    0.59
    letters
    0.59
    Letter
    0.58
    uds
    0.58
     horm
    0.56
     Gram
    0.56
    MAL
    0.56
    Activations Density 1.308%

    No Known Activations