© 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. 4558
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and structures in code

    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
    398
    +0.10
    0.4%
    309
    +0.10
    0.4%
    269
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    561
    +0.10
    0.04
    176
    +0.10
    0.03
    727
    +0.10
    0.04
    Negative Logits
     acknow
    -0.81
     describ
    -0.81
     arrang
    -0.73
    enegger
    -0.70
     neighb
    -0.70
     IMAGES
    -0.70
    >]
    -0.69
     answ
    -0.68
    accompan
    -0.67
     agre
    -0.64
    POSITIVE LOGITS
    inant
    0.69
    onal
    0.67
     Barrel
    0.67
    ());
    0.63
    bid
    0.63
    rosso
    0.62
    enza
    0.61
     Dak
    0.60
    SourceFile
    0.59
    topic
    0.59
    Activations Density 0.820%

    No Known Activations