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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13545
    Prev
    Next
    INDEX
    Explanations

    references to the number two

    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
    756
    +0.16
    1.1%
    721
    +0.16
    1.0%
    253
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.16
    0.02
    762
    +0.16
    0.01
    223
    +0.13
    0.03
    Negative Logits
     Disciple
    -0.67
    ishing
    -0.65
     Ammo
    -0.65
     Nath
    -0.64
    emic
    -0.63
    Ĭ
    -0.62
     Vaj
    -0.60
     Fib
    -0.60
     ammo
    -0.60
     myth
    -0.59
    POSITIVE LOGITS
    say
    1.05
    âĹ¼
    0.80
    ernels
    0.78
    oided
    0.77
    views
    0.76
    vana
    0.74
    livious
    0.73
    olphin
    0.73
    ilogy
    0.72
    anwhile
    0.71
    Activations Density 0.025%

    No Known Activations