© 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. 3436
    Prev
    Next
    INDEX
    Explanations

    terms related to power dynamics and control in contexts like leadership or authority

    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
    497
    +0.19
    0.9%
    481
    +0.15
    0.7%
    756
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.19
    0.16
    169
    +0.15
    0.09
    753
    +0.12
    0.10
    Negative Logits
    imei
    -0.75
    asta
    -0.66
     foreigner
    -0.65
     Zot
    -0.64
     Tanz
    -0.64
    >(
    -0.60
     faint
    -0.59
     Nek
    -0.59
     WHO
    -0.57
     GROUP
    -0.57
    POSITIVE LOGITS
    hyde
    0.72
    theless
    0.70
     adaptations
    0.68
    flix
    0.67
    agra
    0.66
    Demand
    0.65
    ull
    0.64
    ioned
    0.64
    CU
    0.64
    adders
    0.63
    Activations Density 9.641%

    No Known Activations