© 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. 3661
    Prev
    Next
    INDEX
    Explanations

    URLs or links associated with content uploads on specific websites

    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
    683
    +0.12
    0.5%
    44
    +0.09
    0.4%
    99
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.12
    0.01
    683
    +0.09
    0.01
    179
    +0.09
    0.01
    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.78
    ufact
    -0.77
     MAC
    -0.75
    ixir
    -0.71
    ovember
    -0.69
    æĿ
    -0.69
    MAC
    -0.69
    displayText
    -0.68
    clerosis
    -0.67
     Dia
    -0.66
    POSITIVE LOGITS
    uploads
    0.77
    ucket
    0.70
    facebook
    0.68
    upload
    0.65
     heed
    0.62
     IMAGES
    0.60
     Postal
    0.59
    vas
    0.59
     htt
    0.58
     spor
    0.58
    Activations Density 0.082%

    No Known Activations