© 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. 4484
    Prev
    Next
    INDEX
    Explanations

    legal terms and references associated with lawsuits and legal proceedings

    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
    71
    +0.16
    0.7%
    380
    +0.11
    0.5%
    379
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.16
    0.05
    64
    +0.11
    -0.04
    672
    +0.11
    0.04
    Negative Logits
    adelphia
    -0.76
    NetMessage
    -0.74
    ó
    -0.74
    mercial
    -0.74
    SPONSORED
    -0.73
    ioxide
    -0.72
    vironment
    -0.71
    pton
    -0.70
    enegger
    -0.69
    ankind
    -0.69
    POSITIVE LOGITS
     peg
    0.82
     forgot
    0.69
     deficit
    0.68
     Ow
    0.68
     delinquent
    0.63
     Detention
    0.60
     scapego
    0.59
     Lost
    0.59
    miss
    0.59
     dog
    0.59
    Activations Density 0.903%

    No Known Activations