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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3836
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals named Karl

    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
    711
    +0.12
    0.5%
    404
    +0.10
    0.4%
    367
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.01
    711
    +0.10
    0.01
    556
    +0.10
    0.01
    Negative Logits
    ippi
    -0.83
    cially
    -0.81
    VALUE
    -0.75
    jee
    -0.75
    paio
    -0.74
    JUST
    -0.71
    ascript
    -0.70
    itely
    -0.69
    keeping
    -0.69
    mpeg
    -0.69
    POSITIVE LOGITS
     Lund
    0.73
     pockets
    0.69
     Towns
    0.68
     Country
    0.68
     Kamp
    0.68
     Dortmund
    0.67
     Wick
    0.67
     Bundes
    0.66
     Ludwig
    0.64
     Ernst
    0.64
    Activations Density 0.080%

    No Known Activations