© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3799
    Prev
    Next
    INDEX
    Explanations

    actions related to planning and organization

    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
    761
    +0.11
    0.5%
    78
    +0.10
    0.5%
    550
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.11
    0.08
    490
    +0.10
    0.08
    298
    +0.10
    0.06
    Negative Logits
    azeera
    -0.80
    DonaldTrump
    -0.71
    Politics
    -0.71
     subscribers
    -0.67
     gubernatorial
    -0.65
    uctions
    -0.64
    Winged
    -0.64
     listeners
    -0.64
    ikers
    -0.64
     Investig
    -0.62
    POSITIVE LOGITS
    olitan
    0.77
    abouts
    0.69
    )!
    0.68
    rawdownloadcloneembedreportprint
    0.67
     mine
    0.66
     XD
    0.66
    hesis
    0.64
    >>\
    0.62
     ABE
    0.62
     Bella
    0.61
    Activations Density 2.714%

    No Known Activations