Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 128k
    5. 0-ATT_128K-OAI
    6. 13563
    Prev
    Next
    INDEX
    Explanations

    references to groups and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/GPT2-Small-OAI-v5-128k-attn-out-SAEs/v5_128k_layer_0
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    131,072
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_attn_out
    Hook Layer
    0
    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
    515
    +0.17
    1.1%
    659
    +0.16
    1.0%
    132
    +0.15
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.09
    653
    +0.16
    0.06
    620
    +0.15
    -0.01
    Negative Logits
     FANTASY
    -0.82
    é»Ĵ
    -0.78
    IELD
    -0.77
     Cla
    -0.73
     Tide
    -0.71
     EDITION
    -0.71
     Predators
    -0.70
    amina
    -0.69
    PLIC
    -0.68
    nir
    -0.67
    POSITIVE LOGITS
    enced
    0.81
    camp
    0.76
    zai
    0.75
    utor
    0.74
    spons
    0.72
    ouver
    0.71
    gregation
    0.70
     Consortium
    0.68
     membership
    0.67
     housed
    0.67
    Activations Density 1.024%

    No Known Activations