© 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. 3778
    Prev
    Next
    INDEX
    Explanations

    political terminology relating to economic discussions

    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
    71
    +0.18
    0.8%
    254
    +0.12
    0.6%
    552
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.18
    0.24
    254
    +0.12
    0.12
    756
    +0.10
    0.17
    Negative Logits
     Profession
    -0.72
     Act
    -0.72
     Laboratories
    -0.68
     Labs
    -0.67
     Lab
    -0.67
     Adapt
    -0.66
    Studio
    -0.65
     Associates
    -0.65
     Miche
    -0.64
     Emergency
    -0.63
    POSITIVE LOGITS
    olla
    0.79
    vd
    0.76
    urden
    0.74
    iencies
    0.74
    ongs
    0.73
    ixtape
    0.72
    awatts
    0.70
    rued
    0.68
    uddle
    0.68
    assi
    0.68
    Activations Density 9.107%

    No Known Activations