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. 13595
    Prev
    Next
    INDEX
    Explanations

    numerical ratings or scores related to various subjects

    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
    270
    +0.19
    1.3%
    566
    +0.19
    1.3%
    64
    +0.18
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    64
    +0.19
    -0.01
    724
    +0.19
    0.04
    720
    +0.18
    0.05
    Negative Logits
    advertising
    -0.99
    Synopsis
    -0.91
    Newsletter
    -0.80
    ################################
    -0.80
     ];
    -0.80
    =-=-=-=-=-=-=-=-
    -0.79
    Craft
    -0.78
    Insert
    -0.78
    Ing
    -0.77
    Attempts
    -0.77
    POSITIVE LOGITS
     Seym
    0.86
     mosqu
    0.76
     satell
    0.74
    ©¶æ
    0.73
     unilateral
    0.71
     rul
    0.70
     mortgages
    0.70
     wiring
    0.69
     inspecting
    0.69
     fung
    0.67
    Activations Density 0.102%

    No Known Activations