© 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. 3073
    Prev
    Next
    INDEX
    Explanations

    titles and references related to narratives or story elements, specifically in fandom contexts

    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
    161
    +0.10
    0.4%
    521
    +0.09
    0.4%
    597
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.10
    373
    +0.09
    0.03
    138
    +0.09
    0.03
    Negative Logits
     UNCLASSIFIED
    -0.97
    kefeller
    -0.92
    anooga
    -0.80
    esty
    -0.79
    ierre
    -0.77
     IoT
    -0.74
    ilies
    -0.73
     responsibly
    -0.72
    ensable
    -0.71
    tnc
    -0.71
    POSITIVE LOGITS
     Edit
    0.90
     Assass
    0.79
     Grimoire
    0.75
     Hallow
    0.74
     Assassins
    0.72
     Scan
    0.72
     Wrestle
    0.71
     Assassin
    0.70
     Dungeons
    0.70
     Credits
    0.70
    Activations Density 1.465%

    No Known Activations