© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 4183
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to statistical terms and numerical data

    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
    459
    +0.16
    0.7%
    715
    +0.11
    0.5%
    126
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.16
    0.06
    521
    +0.11
    0.05
    464
    +0.11
    0.05
    Negative Logits
    theless
    -0.97
    MpServer
    -0.73
    successfully
    -0.69
    EStream
    -0.68
     orcs
    -0.68
    borgh
    -0.65
     recip
    -0.65
    ammy
    -0.64
    ã
    -0.64
    aeda
    -0.64
    POSITIVE LOGITS
     Wake
    0.70
    heit
    0.69
    lishes
    0.66
     Bunker
    0.64
     resort
    0.59
    poll
    0.58
     rush
    0.58
    perature
    0.58
    ¸
    0.58
    ع
    0.57
    Activations Density 1.761%

    No Known Activations