© 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. 3344
    Prev
    Next
    INDEX
    Explanations

    phrases related to temptation or the act of being tempted

    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
    761
    +0.11
    0.5%
    633
    +0.10
    0.5%
    435
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    510
    +0.11
    0.02
    435
    +0.10
    0.02
    689
    +0.09
    0.01
    Negative Logits
     streng
    -0.71
     notified
    -0.69
     testament
    -0.67
    tip
    -0.67
    INST
    -0.66
    EMENT
    -0.64
    Staff
    -0.64
    number
    -0.63
     Nationwide
    -0.62
    Breaking
    -0.62
    POSITIVE LOGITS
     pitfalls
    0.93
    essim
    0.83
     temptation
    0.79
    ammers
    0.78
     underest
    0.75
     traps
    0.75
     desserts
    0.73
    irgin
    0.73
    bably
    0.70
     compromises
    0.70
    Activations Density 0.192%

    No Known Activations