© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3163
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their attributes in contexts related to sports or talent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.3.hook_attn_out
    Hook Layer
    3
    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
    105
    +0.13
    0.6%
    579
    +0.09
    0.4%
    168
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.13
    0.02
    105
    +0.09
    0.01
    501
    +0.09
    0.01
    Negative Logits
     Upton
    -0.62
    sole
    -0.59
     unint
    -0.57
     Frieza
    -0.57
    akeru
    -0.57
    race
    -0.57
    erm
    -0.57
    iliary
    -0.57
     veterin
    -0.56
    olescent
    -0.56
    POSITIVE LOGITS
    ï¸ı
    0.72
    berger
    0.71
    anka
    0.67
    hare
    0.67
    tics
    0.64
    cker
    0.63
    Brand
    0.62
    bart
    0.61
    baugh
    0.61
    ãĥij
    0.61
    Activations Density 0.060%

    No Known Activations