© 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. 4458
    Prev
    Next
    INDEX
    Explanations

    numerical data and specifications

    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
    756
    +0.14
    0.7%
    420
    +0.12
    0.5%
    473
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    -0.01
    473
    +0.12
    0.05
    420
    +0.10
    -0.01
    Negative Logits
     Har
    -0.63
     Cannabis
    -0.62
     Vaughan
    -0.60
    opa
    -0.59
     Palest
    -0.59
     Marijuana
    -0.58
     Oxy
    -0.58
     Berman
    -0.58
     MPH
    -0.57
     Californ
    -0.57
    POSITIVE LOGITS
    ozyg
    0.86
    soDeliveryDate
    0.80
    ogh
    0.78
    urized
    0.70
    sonian
    0.70
    iona
    0.67
    addons
    0.65
    dfx
    0.64
     embodiments
    0.63
    successful
    0.63
    Activations Density 3.055%

    No Known Activations