© 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. 4525
    Prev
    Next
    INDEX
    Explanations

    terms related to algorithms and their applications

    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
    494
    +0.11
    0.5%
    349
    +0.10
    0.4%
    32
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.11
    0.04
    264
    +0.10
    0.03
    447
    +0.09
    0.05
    Negative Logits
    pace
    -0.72
    sole
    -0.69
    ifest
    -0.68
    lance
    -0.66
    mil
    -0.64
    SPA
    -0.63
    ovember
    -0.62
    owship
    -0.62
    Tea
    -0.61
     nonex
    -0.61
    POSITIVE LOGITS
    ©¶æ
    0.86
    igl
    0.66
    ellery
    0.62
     Scores
    0.62
    anooga
    0.62
    Ü
    0.62
    glers
    0.62
    èĢħ
    0.59
    ulhu
    0.58
    ellen
    0.58
    Activations Density 0.397%

    No Known Activations