© 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. 3823
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and data structures

    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
    373
    +0.14
    0.6%
    71
    +0.12
    0.5%
    72
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.14
    0.17
    700
    +0.12
    0.09
    756
    +0.10
    0.11
    Negative Logits
    ometimes
    -0.89
    ograp
    -0.76
    ividual
    -0.69
    lishing
    -0.67
    inventoryQuantity
    -0.67
    embed
    -0.66
    ographically
    -0.65
    ulhu
    -0.64
    ographed
    -0.64
    ousands
    -0.63
    POSITIVE LOGITS
     attRot
    0.76
     Jr
    0.69
    Elf
    0.67
     Steele
    0.64
    agan
    0.63
    æĢ
    0.63
     Muse
    0.62
    IAS
    0.58
    º
    0.58
    Pri
    0.58
    Activations Density 5.357%

    No Known Activations