© 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. 3485
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and documents

    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
    84
    +0.12
    0.6%
    481
    +0.11
    0.5%
    234
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.12
    0.20
    481
    +0.11
    0.26
    291
    +0.10
    0.15
    Negative Logits
     horm
    -0.71
     slee
    -0.70
     Nerd
    -0.69
     sob
    -0.67
    cffffcc
    -0.67
     reader
    -0.66
    emonic
    -0.65
    »Ĵ
    -0.63
    ween
    -0.62
     wat
    -0.60
    POSITIVE LOGITS
    discrimination
    0.65
     guiActiveUnfocused
    0.63
    nels
    0.62
    FILE
    0.60
     unlawfully
    0.59
    utes
    0.59
     Cot
    0.58
     copyrighted
    0.57
    their
    0.57
     arrang
    0.57
    Activations Density 13.401%

    No Known Activations