© 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. 3094
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Doug" and its variations

    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
    337
    +0.11
    0.5%
    676
    +0.10
    0.5%
    333
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.02
    521
    +0.10
    0.02
    120
    +0.10
    0.02
    Negative Logits
    uko
    -0.67
    arez
    -0.67
    Las
    -0.65
     Hasan
    -0.65
    ayn
    -0.64
    ibo
    -0.63
    Brit
    -0.62
    aceae
    -0.60
    ãĥķãĤ©
    -0.59
    ulet
    -0.58
    POSITIVE LOGITS
     intern
    0.66
    alore
    0.62
    bourne
    0.62
    burn
    0.62
    fee
    0.60
    lder
    0.60
     commuting
    0.59
    emouth
    0.59
    herer
    0.59
    chnology
    0.58
    Activations Density 0.138%

    No Known Activations