© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4354
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and 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
    602
    +0.13
    0.6%
    243
    +0.11
    0.5%
    756
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    742
    +0.13
    0.06
    294
    +0.11
    0.04
    212
    +0.10
    0.04
    Negative Logits
     Lauder
    -0.82
     Amid
    -0.68
     Personality
    -0.67
     Yong
    -0.66
     laureate
    -0.66
    aird
    -0.65
    .,"
    -0.63
     Archae
    -0.63
    Ãį
    -0.62
     Yin
    -0.61
    POSITIVE LOGITS
    cknow
    0.85
    ?)
    0.76
    )=
    0.75
    ãĥ¼ãĥĨãĤ£
    0.73
    ãĥĥãĤ¯
    0.73
    rats
    0.72
    Reloaded
    0.72
    phia
    0.70
     impossibility
    0.69
    ucer
    0.67
    Activations Density 1.444%

    No Known Activations