© 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. 3502
    Prev
    Next
    INDEX
    Explanations

    imperative statements or suggestions regarding actions or policies

    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
    551
    +0.11
    0.5%
    459
    +0.10
    0.5%
    641
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.11
    0.04
    446
    +0.10
    0.04
    618
    +0.10
    0.04
    Negative Logits
     Legion
    -0.66
     Estate
    -0.64
     ISP
    -0.64
     tang
    -0.63
     legion
    -0.62
     LT
    -0.61
     Bulg
    -0.61
     IB
    -0.61
     Odyssey
    -0.61
     Typhoon
    -0.60
    POSITIVE LOGITS
    é¾įå
    0.95
    ocate
    0.94
    anship
    0.81
    arsh
    0.78
    ocally
    0.77
    zeb
    0.74
    onom
    0.74
    ounters
    0.73
    utterstock
    0.73
    imester
    0.73
    Activations Density 1.246%

    No Known Activations