© 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. 3249
    Prev
    Next
    INDEX
    Explanations

    references to vice presidents and their positions

    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
    218
    +0.12
    0.5%
    88
    +0.12
    0.5%
    454
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    179
    +0.12
    0.03
    328
    +0.12
    0.02
    730
    +0.10
    0.03
    Negative Logits
    UI
    -0.72
    mouse
    -0.67
    util
    -0.67
    aylor
    -0.64
    emouth
    -0.63
    ellen
    -0.62
    olon
    -0.59
    tu
    -0.59
     acre
    -0.59
    leground
    -0.59
    POSITIVE LOGITS
     Pact
    0.89
    rency
    0.75
     Eps
    0.69
    acts
    0.65
     derog
    0.64
    bol
    0.64
     Hatch
    0.63
    rences
    0.63
    aith
    0.63
    tails
    0.63
    Activations Density 0.516%

    No Known Activations