© 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. 3901
    Prev
    Next
    INDEX
    Explanations

    references to flavor and related concepts

    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
    650
    +0.12
    0.6%
    365
    +0.12
    0.5%
    332
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.12
    0.03
    365
    +0.12
    0.02
    535
    +0.12
    0.02
    Negative Logits
    anamo
    -0.81
    schild
    -0.80
    ptions
    -0.77
    aniel
    -0.76
    ploy
    -0.74
    rences
    -0.73
    ithing
    -0.73
    ropolitan
    -0.72
     Telephone
    -0.71
    itals
    -0.71
    POSITIVE LOGITS
     aroma
    0.93
    terness
    0.90
     flavor
    0.87
     Gujar
    0.82
     flavors
    0.79
     arom
    0.78
     additive
    0.76
     Flav
    0.73
     coloring
    0.72
     yeast
    0.71
    Activations Density 0.278%

    No Known Activations