© 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. 3559
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of breadth or diversity in various 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
    547
    +0.13
    0.6%
    225
    +0.11
    0.5%
    199
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    547
    +0.13
    0.02
    225
    +0.11
    0.03
    160
    +0.10
    0.02
    Negative Logits
     Keeper
    -0.86
    araoh
    -0.76
     mummy
    -0.73
    ammy
    -0.72
     Kira
    -0.67
     Avalon
    -0.65
    itely
    -0.64
     fug
    -0.63
     Plato
    -0.63
     cop
    -0.61
    POSITIVE LOGITS
    soType
    0.99
    displayText
    0.87
    actionDate
    0.85
    ãĤ¼ãĤ¦ãĤ¹
    0.84
    wow
    0.83
    xual
    0.81
    channelAvailability
    0.79
     behavi
    0.78
    earable
    0.78
    ======
    0.76
    Activations Density 0.315%

    No Known Activations