© 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. 3404
    Prev
    Next
    INDEX
    Explanations

    references to the United States and its geopolitical actions

    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
    465
    +0.12
    0.6%
    136
    +0.10
    0.5%
    291
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    632
    +0.12
    0.05
    763
    +0.10
    0.05
    115
    +0.09
    0.04
    Negative Logits
     Eps
    -0.66
     Cheong
    -0.64
     Murray
    -0.64
    iencies
    -0.63
    chio
    -0.62
     Metatron
    -0.62
     Mighty
    -0.61
     VG
    -0.61
    hy
    -0.60
     Pog
    -0.60
    POSITIVE LOGITS
     ILCS
    0.79
    oval
    0.68
    going
    0.66
    gress
    0.65
    igslist
    0.64
    panic
    0.64
    isSpecialOrderable
    0.63
    ccording
    0.63
    Leaks
    0.61
     unsus
    0.61
    Activations Density 0.345%

    No Known Activations