© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3182
    Prev
    Next
    INDEX
    Explanations

    inquiries or conditions regarding the ability to do something without specific limitations or requirements

    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
    123
    +0.12
    0.5%
    342
    +0.11
    0.5%
    70
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    0.10
    70
    +0.11
    0.08
    342
    +0.11
    0.07
    Negative Logits
    Cath
    -0.69
     Kard
    -0.66
     Pil
    -0.65
     Cath
    -0.65
     Pon
    -0.65
    è¦
    -0.62
     Ori
    -0.62
     Fell
    -0.61
    entin
    -0.61
     Poles
    -0.60
    POSITIVE LOGITS
     easily
    0.94
     safely
    0.91
     efficiently
    0.81
     comfortably
    0.78
    ivably
    0.76
     seamlessly
    0.75
     customize
    0.75
     sustain
    0.75
     browse
    0.75
     independently
    0.74
    Activations Density 3.190%

    No Known Activations