© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3445
    Prev
    Next
    INDEX
    Explanations

    complex and nuanced emotional expressions

    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
    458
    +0.11
    0.5%
    229
    +0.10
    0.4%
    259
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.11
    0.06
    611
    +0.10
    0.08
    313
    +0.09
    0.06
    Negative Logits
    erial
    -0.76
    lite
    -0.74
    etter
    -0.74
    istine
    -0.73
    seys
    -0.73
    tty
    -0.73
    acement
    -0.71
    liga
    -0.71
    udder
    -0.71
    igs
    -0.70
    POSITIVE LOGITS
     Meditation
    0.83
     Drugs
    0.83
     Humanity
    0.77
     Pharmaceutical
    0.73
     Influence
    0.73
     Studios
    0.72
     Rac
    0.69
     Mana
    0.69
     Psychological
    0.69
     Mind
    0.68
    Activations Density 1.662%

    No Known Activations