© 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. 3265
    Prev
    Next
    INDEX
    Explanations

    arguments and sentiments related to political opinions and societal issues

    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
    745
    +0.12
    0.5%
    321
    +0.10
    0.4%
    81
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.12
    0.13
    693
    +0.10
    0.13
    71
    +0.09
    0.03
    Negative Logits
    agog
    -0.72
     ______
    -0.69
    storage
    -0.65
    ubes
    -0.64
     Statue
    -0.64
    readable
    -0.64
     depos
    -0.63
    rored
    -0.62
    lamm
    -0.61
    orescent
    -0.60
    POSITIVE LOGITS
     prem
    0.75
    kamp
    0.73
     charisma
    0.72
    ãĤ´ãĥ³
    0.72
    Õ
    0.70
    PF
    0.68
    hammad
    0.68
    ï¸
    0.68
    ©¶æ¥µ
    0.67
    ®
    0.65
    Activations Density 30.248%

    No Known Activations