© 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. 3158
    Prev
    Next
    INDEX
    Explanations

    phrases related to voting and political decisions

    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
    28
    +0.12
    0.5%
    50
    +0.10
    0.5%
    15
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.12
    0.03
    62
    +0.10
    0.03
    163
    +0.10
    0.03
    Negative Logits
    paralle
    -0.72
    Cam
    -0.70
    OWS
    -0.67
    stood
    -0.64
    fol
    -0.64
    mouth
    -0.64
    interstitial
    -0.63
    vik
    -0.63
    uded
    -0.62
    Writer
    -0.62
    POSITIVE LOGITS
    galitarian
    0.82
     Zup
    0.74
     feder
    0.74
    eday
    0.72
     =>
    0.72
     democratically
    0.67
     defer
    0.66
    azar
    0.66
     forfeit
    0.63
     Garland
    0.61
    Activations Density 0.319%

    No Known Activations