© 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. 3453
    Prev
    Next
    INDEX
    Explanations

    references to conventions and events, particularly with an emphasis on attendance and experiences

    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
    379
    +0.10
    0.4%
    450
    +0.09
    0.4%
    631
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.10
    0.03
    300
    +0.09
    0.02
    57
    +0.09
    0.02
    Negative Logits
    ĸļ
    -0.80
    Fax
    -0.77
    pload
    -0.69
    ãĥ¼ãĥ
    -0.68
    schild
    -0.66
    enthal
    -0.65
    clips
    -0.64
    pak
    -0.62
    velt
    -0.61
    odan
    -0.61
    POSITIVE LOGITS
     Horses
    0.71
    rosso
    0.67
     Cance
    0.64
    ismo
    0.63
     nominate
    0.61
     Breakfast
    0.61
    Style
    0.61
    rio
    0.61
    rules
    0.60
    tro
    0.60
    Activations Density 0.945%

    No Known Activations