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. 13557
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "of"

    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
    266
    +0.20
    1.3%
    59
    +0.15
    1.0%
    336
    +0.15
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    218
    +0.20
    0.04
    97
    +0.15
    0.06
    480
    +0.15
    0.05
    Negative Logits
    uyomi
    -0.76
    govtrack
    -0.75
    accompan
    -0.74
    liga
    -0.73
    andowski
    -0.72
    wana
    -0.72
     legalized
    -0.70
     Referred
    -0.69
    âĵĺ
    -0.69
     museums
    -0.69
    POSITIVE LOGITS
    glers
    0.79
    --+
    0.75
    ongevity
    0.74
    :(
    0.73
    odiac
    0.72
    ++++
    0.71
    #$
    0.71
    ãĥ£
    0.70
    phies
    0.67
    ^{
    0.67
    Activations Density 0.493%

    No Known Activations