© 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. 4076
    Prev
    Next
    INDEX
    Explanations

    topics related to voting laws and voter suppression issues

    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
    233
    +0.14
    0.6%
    696
    +0.10
    0.5%
    478
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    754
    +0.14
    0.08
    447
    +0.10
    0.10
    153
    +0.10
    0.07
    Negative Logits
    £
    -0.83
    âķIJâķIJ
    -0.79
    ĪĴ
    -0.75
    ľ
    -0.74
     earnest
    -0.68
    JJ
    -0.68
    Downloadha
    -0.65
    Browser
    -0.64
    âĸijâĸij
    -0.63
    ãĥ¯ãĥ³
    -0.61
    POSITIVE LOGITS
    nesses
    0.75
    ment
    0.67
     syndrome
    0.67
    sburg
    0.65
    cum
    0.64
     Awareness
    0.64
    central
    0.63
     Cosponsors
    0.63
    cent
    0.63
    center
    0.62
    Activations Density 1.476%

    No Known Activations