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. 13590
    Prev
    Next
    INDEX
    Explanations

    instances of the word "vegan" and its variations

    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
    651
    +0.19
    1.4%
    339
    +0.17
    1.3%
    101
    +0.16
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.19
    0.03
    326
    +0.17
    0.02
    447
    +0.16
    0.02
    Negative Logits
    essor
    -0.84
    channelAvailability
    -0.83
    ģĸ
    -0.76
    eday
    -0.71
     Polk
    -0.71
    aternity
    -0.71
    ederal
    -0.70
     Dow
    -0.70
    iami
    -0.69
    OTUS
    -0.68
    POSITIVE LOGITS
    glers
    0.89
    etooth
    0.80
     flavours
    0.79
     gust
    0.77
    Motion
    0.77
     salads
    0.76
     jams
    0.76
    bats
    0.75
    iHUD
    0.73
    inia
    0.73
    Activations Density 0.047%

    No Known Activations