© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3758
    Prev
    Next
    INDEX
    Explanations

    references to evil and its various manifestations

    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
    572
    +0.12
    0.5%
    581
    +0.10
    0.4%
    690
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.12
    0.02
    516
    +0.10
    0.02
    141
    +0.10
    0.01
    Negative Logits
    igham
    -0.90
    essional
    -0.86
    ritz
    -0.77
    veland
    -0.72
    etus
    -0.71
    ousse
    -0.70
    anut
    -0.70
    clus
    -0.69
    ÄŁ
    -0.64
    ecd
    -0.64
    POSITIVE LOGITS
     counterfe
    0.79
     Ultron
    0.77
     Loki
    0.73
     greed
    0.71
     Faust
    0.69
     Metatron
    0.69
     Lucifer
    0.68
     plotted
    0.66
     treason
    0.66
     Demons
    0.65
    Activations Density 0.356%

    No Known Activations