© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3879
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to software development and project management

    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
    643
    +0.11
    0.5%
    28
    +0.10
    0.5%
    186
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.11
    0.08
    680
    +0.10
    0.06
    64
    +0.10
    -0.15
    Negative Logits
    interstitial
    -0.87
    anos
    -0.80
     tsunami
    -0.76
    insula
    -0.76
    neapolis
    -0.73
    iley
    -0.70
    ooming
    -0.66
    Buyable
    -0.66
    ipeg
    -0.66
    inventoryQuantity
    -0.65
    POSITIVE LOGITS
     sacrific
    0.80
     certific
    0.75
     administr
    0.73
     submit
    0.68
     manually
    0.67
     administrators
    0.67
     Almighty
    0.65
     Berm
    0.63
     submitting
    0.63
     Letters
    0.62
    Activations Density 9.882%

    No Known Activations