© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4434
    Prev
    Next
    INDEX
    Explanations

    URLs or links, particularly those related to video and image content

    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
    688
    +0.13
    0.6%
    342
    +0.09
    0.4%
    643
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.13
    0.02
    313
    +0.09
    0.02
    270
    +0.09
    0.02
    Negative Logits
     acknowled
    -0.80
     territ
    -0.73
     particulars
    -0.72
     retaining
    -0.72
     endif
    -0.69
     integ
    -0.69
     retain
    -0.68
     incorpor
    -0.64
     extant
    -0.63
     latitude
    -0.62
    POSITIVE LOGITS
     è£ıç
    0.91
     Tomorrow
    0.83
    ãĥĺ
    0.79
    ãĤ§
    0.78
     Falk
    0.74
    Morning
    0.73
    "))
    0.71
     Pumpkin
    0.69
    ').
    0.67
    )",
    0.67
    Activations Density 0.130%

    No Known Activations